© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8866
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    2.12
    া
    2.04
     waarmee
    1.70
    ci
    1.70
     وطالبات
    1.69
    glas
    1.66
    ように
    1.64
    clearfix
    1.64
    nent
    1.59
    Retrie
    1.59
    POSITIVE LOGITS
    ো
    1.91
    ্ক
    1.73
    🅽
    1.67
    א
    1.61
     iba
    1.60
    िंग
    1.58
     bribes
    1.58
    感じ
    1.57
    ità
    1.56
    아요
    1.56
    Activations Density 0.185%

    No Known Activations