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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6160
    Prev
    Next
    INDEX
    Explanations

    numbers that may be prices

    oai_token-act-pair · gemini-2.0-flash

    numeric or financial terms

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

    prices

    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
     ligation
    -0.47
    QSize
    -0.45
     nouns
    -0.44
    uestos
    -0.44
     minib
    -0.43
    AddHtmlAttribute
    -0.42
     nodules
    -0.41
     nodule
    -0.41
     six
    -0.41
     chestnuts
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.72
    AsUp
    0.72
    GEBURTSDATUM
    0.70
    InitVars
    0.70
    -------------</
    0.69
     Biôgrafia
    0.66
    ConstraintMaker
    0.65
     himo
    0.64
    __*/
    0.64
    +#+#
    0.63
    Activations Density 1.353%

    No Known Activations