© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6503
    Prev
    Next
    INDEX
    Explanations

    law citations and legal documents

    oai_token-act-pair · gemini-2.0-flash

    Legal/policy documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ReusableCell
    -0.72
    ########.
    -0.67
    RectangleBorder
    -0.65
    expandindo
    -0.63
     متعلقه
    -0.58
     Paglinawan
    -0.58
     ModelExpression
    -0.56
     Италијани
    -0.54
     Dernière
    -0.54
    IndentedString
    -0.54
    POSITIVE LOGITS
     ✭✭
    0.56
     getItemCount
    0.52
     VIAF
    0.52
    EndProject
    0.51
     imper
    0.50
    istung
    0.48
    ارض
    0.48
     appré
    0.47
    batore
    0.47
    maquilla
    0.47
    Activations Density 2.007%

    No Known Activations