© 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. 4476
    Prev
    Next
    INDEX
    Explanations

    mentions of personal pronouns and hair

    oai_token-act-pair · gemini-2.0-flash

    hair

    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
     feroit
    -1.01
     avoient
    -0.99
     auroit
    -0.96
     Romains
    -0.96
     malheure
    -0.96
     enfans
    -0.95
     pouvoit
    -0.95
     effray
    -0.94
     disant
    -0.93
     figliu
    -0.93
    POSITIVE LOGITS
     ModelExpression
    0.85
     autorytatywna
    0.83
     "
    0.79
    RenderAtEndOf
    0.79
     EconPapers
    0.78
    enterOuterAlt
    0.77
    awtextra
    0.76
     initComponents
    0.76
     insuffisamment
    0.71
     GenerationType
    0.69
    Activations Density 2.686%

    No Known Activations