© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4687
    Prev
    Next
    INDEX
    Explanations

    heatmap, geodata, visualization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.93
    tica
    0.88
    l
    0.87
    op
    0.86
    كله
    0.81
    is
    0.81
    Nach
    0.80
    ท
    0.79
    isme
    0.79
    sp
    0.77
    POSITIVE LOGITS
     totalSupply
    1.00
    \`
    0.99
    शाली
    0.94
     neutroph
    0.93
    ی
    0.91
    ponym
    0.90
    giveness
    0.88
    referrer
    0.88
    രുവനന്തപു
    0.87
     biomarkers
    0.87
    Activations Density 0.002%

    No Known Activations