© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13125
    Prev
    Next
    INDEX
    Explanations

    jargon terms and brand names associated with consumer products

    oai_token-act-pair · gemini-2.0-flash

    Energy and sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     تانيه
    -0.60
    BufferException
    -0.55
     atraves
    -0.54
    SharedCtor
    -0.52
    Nuorodos
    -0.50
    iostream
    -0.50
    DrawerToggle
    -0.50
    fromString
    -0.50
    icolon
    -0.50
    aarrggbb
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیا
    0.84
    وفة
    0.63
     Wiktionnaire
    0.57
     BytesLike
    0.57
     ModelExpression
    0.55
    ISupport
    0.52
    IsMutable
    0.51
     getItemCount
    0.50
    例文帳に追加
    0.50
     elettrico
    0.49
    Activations Density 8.646%

    No Known Activations