© 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. 8908
    Prev
    Next
    INDEX
    Explanations

    wattpad or launchpad

    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
    ement
    0.74
    ene
    0.72
    enea
    0.71
     previa
    0.70
    书
    0.70
    ות
    0.69
     warum
    0.68
    ige
    0.68
    ैंड
    0.67
    ﻥ
    0.67
    POSITIVE LOGITS
    s
    0.70
     оформления
    0.69
    郸
    0.63
     UITableViewCell
    0.63
    ಯಲ್ಲಿ
    0.62
    гыз
    0.62
    🔥🔥
    0.62
    pathetic
    0.61
    ्स
    0.61
    keyDown
    0.60
    Activations Density 0.003%

    No Known Activations