© 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. 9183
    Prev
    Next
    INDEX
    Explanations

    https://

    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
    ли
    1.20
    hii
    1.19
    𝒕
    1.17
    𝒂
    1.17
    𝒊
    1.12
    情况下
    1.11
    HING
    1.08
    𝒖
    1.06
    ше
    1.06
    窕
    1.05
    POSITIVE LOGITS
     expiresIn
    1.04
    开展
    0.99
    ام
    0.97
    ணிய
    0.96
     गठित
    0.96
    楽器
    0.94
    ezza
    0.93
     Praise
    0.93
    er
    0.93
     spéciale
    0.93
    Activations Density 0.027%

    No Known Activations