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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9937
    Prev
    Next
    INDEX
    Explanations

    instances of the word "are, you're, or if" followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    phrases related to seeking or searching

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

    searching

    np_max-act-logits · gemini-2.0-flash
    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
     disambiguazione
    -0.64
    AndEndTag
    -0.63
    rungsseite
    -0.60
    kháu
    -0.57
    Kaynakça
    -0.52
     Administrativna
    -0.52
    KURZBESCHREIBUNG
    -0.52
    braith
    -0.51
     ostavi
    -0.50
     FetchType
    -0.49
    POSITIVE LOGITS
     seeking
    0.68
    UnusedPrivate
    0.67
     planning
    0.66
     Roskov
    0.65
     attending
    0.65
     searching
    0.64
     trying
    0.63
     looking
    0.60
    queryInterface
    0.59
     chasing
    0.59
    Activations Density 0.716%

    No Known Activations