© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11354
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate comparisons

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    migrationBuilder
    -0.71
    ABAD
    -0.66
    ADATA
    -0.65
    WriteLiteral
    -0.61
     BitmapFactory
    -0.61
    fjspx
    -0.59
    peka
    -0.59
    Espèce
    -0.58
    참고
    -0.58
    HttpFoundation
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.47
    richTextPanel
    0.46
     Administrativna
    0.45
     pertes
    0.43
    hit
    0.43
    gesellschaft
    0.43
     térmica
    0.42
    trans
    0.42
     preuves
    0.42
    entgen
    0.42
    Activations Density 8.729%

    No Known Activations