© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8620
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
    s
    2.46
    ों
    2.33
    人
    2.32
    iş
    2.31
    ੀ
    2.23
    ისუფ
    2.15
    იმ
    2.14
    er
    2.09
    l
    2.07
    seign
    2.05
    POSITIVE LOGITS
     Interested
    2.04
     Божи
    2.00
     iesp
    1.93
     Reasoning
    1.90
    hasClass
    1.90
    Taste
    1.87
     grown
    1.85
    특별시
    1.85
     средствами
    1.84
    getRow
    1.84
    Activations Density 0.021%

    No Known Activations