© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12516
    Prev
    Next
    INDEX
    Explanations

    references to a celebrity named Iggy Azalea as well as general references to rappers and the word rapper.

    oai_token-act-pair · gemini-2.0-flash

    phrases related to identity and personal information

    np_token-act-pair-logits · gpt-4o-mini

    Musicians and rappers

    np_max-act-logits · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.82
    WebControls
    -0.59
    glBegin
    -0.59
     jScrollPane
    -0.56
    ++];
    -0.56
    ărul
    -0.55
     chêne
    -0.54
     DialogInterface
    -0.53
     invokingState
    -0.53
     pinulongan
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.69
    Tikang
    0.55
     Réponses
    0.54
    kuuta
    0.53
    ########.
    0.51
     Drapeau
    0.47
     lenker
    0.47
    MigrationBuilder
    0.46
     pop
    0.46
    AccessorTable
    0.46
    Activations Density 1.239%

    No Known Activations