© 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. 8894
    Prev
    Next
    INDEX
    Explanations

    all of a sudden

    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
    ^{-}
    2.08
     gören
    1.70
    𝖘
    1.69
    पूर्ण
    1.67
    
    1.67
    𝚂
    1.56
     νέ
    1.55
    ^{*}
    1.55
    ^{-}$
    1.54
    𝓸
    1.53
    POSITIVE LOGITS
    া
    1.76
    ส์
    1.57
     dovuto
    1.50
    eness
    1.44
     মতো
    1.44
     lưới
    1.42
    प
    1.41
     Conjecture
    1.35
    quake
    1.34
    ा
    1.34
    Activations Density 0.000%

    No Known Activations