© 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. 9073
    Prev
    Next
    INDEX
    Explanations

    socioeconomic

    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
    থাৎ
    0.63
    d
    0.57
    aş
    0.57
    cieron
    0.57
     forbidding
    0.56
    ^{-}
    0.54
     ການ
    0.53
    dies
    0.53
    days
    0.52
     sufficiency
    0.52
    POSITIVE LOGITS
    ه
    0.70
    INFRINGEMENT
    0.54
    ᆼ
    0.54
    ല
    0.54
    ㅂ
    0.53
    য়
    0.53
     tras
    0.52
    𝗠
    0.51
    ᆫ
    0.51
    چه
    0.51
    Activations Density 0.002%

    No Known Activations