© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15099
    Prev
    Next
    INDEX
    Explanations

    text directly pertaining to unlawful activity in legal or political contexts

    oai_token-act-pair · gemini-2.0-flash

    illegal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -0.90
     doubtnut
    -0.89
     Partagez
    -0.82
     itſelf
    -0.82
     laiss
    -0.82
     becauſe
    -0.77
     ་་
    -0.76
     mergeFrom
    -0.75
    wpi
    -0.75
     Diſ
    -0.75
    POSITIVE LOGITS
    SizeMode
    0.63
     getS
    0.59
    LayoutStyle
    0.59
     للاسماء
    0.59
    dragen
    0.56
     col
    0.53
     {
    0.52
    рации
    0.52
    columbia
    0.52
    principalColumn
    0.52
    Activations Density 3.377%

    No Known Activations