© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    react import statements

    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
    Negative Logits
     behest
    2.10
    i
    2.08
    ма
    2.06
    <0xBE>
    1.97
    錒
    1.94
     poté
    1.91
    د
    1.85
    て
    1.84
    ی
    1.83
    其中的
    1.82
    POSITIVE LOGITS
    fw
    2.14
    tedir
    1.90
     trợ
    1.82
    fq
    1.79
    इजेशन
    1.78
    parity
    1.76
    mais
    1.76
     teller
    1.75
     nies
    1.75
     scars
    1.75
    Activations Density 0.004%

    No Known Activations