© 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. 9076
    Prev
    Next
    INDEX
    Explanations

    learned scholars scholarly

    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
     बेसब्री
    1.96
    extras
    1.84
     bylaws
    1.83
    ające
    1.82
     summarise
    1.79
     payoff
    1.78
     работода
    1.76
     پاس
    1.72
    chsel
    1.71
    ජ
    1.70
    POSITIVE LOGITS
    ת
    1.99
    מ
    1.95
     ši
    1.87
     متغير
    1.84
    ouring
    1.80
    <bos>
    1.79
     tae
    1.77
    ์
    1.77
    at
    1.77
     ইঙ্গ
    1.76
    Activations Density 0.052%

    No Known Activations