© 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. 11446
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Underscores and hyphens

    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
     للاسماء
    -0.91
     autorytatywna
    -0.77
     himſelf
    -0.75
     بيها
    -0.75
     myſelf
    -0.74
    Билгалдахарш
    -0.73
     ſhould
    -0.70
     estekak
    -0.70
    Fordítás
    -0.69
     kaarangay
    -0.69
    POSITIVE LOGITS
    </i>
    0.46
     Stakes
    0.43
     CARE
    0.42
    ateg
    0.41
     TextAppearance
    0.41
     Care
    0.40
    Redund
    0.40
    eral
    0.40
    ken
    0.40
     Alleg
    0.39
    Activations Density 2.392%

    No Known Activations