© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176281
    Prev
    Next
    INDEX
    Explanations

    code parsing non-english tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    0
    0.53
    Ex
    0.47
    by
    0.46
    P
    0.44
    Human
    0.43
    ck
    0.43
    from
    0.43
    ave
    0.43
     Human
    0.42
    1
    0.42
    POSITIVE LOGITS
    𒅗
    0.57
     участка
    0.50
    icación
    0.50
    ைகளைக்
    0.50
     قلت
    0.48
     usamos
    0.47
    ţiile
    0.46
     اقصیٰ
    0.46
    𒀀
    0.46
     스트
    0.46
    Activations Density 0.000%

    No Known Activations