© 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. 8895
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and Pinyin

    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
    ただし
    1.57
     escenario
    1.46
     apothe
    1.31
    ub
    1.27
    зой
    1.24
    serde
    1.23
    ′-
    1.21
    ста
    1.20
    $)
    1.20
    wrapperEl
    1.19
    POSITIVE LOGITS
    dard
    1.82
    ן
    1.76
    ics
    1.71
    ariance
    1.71
     joystick
    1.70
    া
    1.69
     beak
    1.69
    ಿತ್ತು
    1.66
    يات
    1.65
    chandise
    1.65
    Activations Density 0.001%

    No Known Activations