© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150300
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    ,(
    0.40
    .,
    0.35
    ,
    0.34
    差别
    0.33
    ,//
    0.33
     স্বয়ং
    0.32
     dissimilar
    0.31
    籃
    0.31
    異
    0.31
    差別
    0.31
    POSITIVE LOGITS
    .
    0.97
    !”.
    0.74
    \\.
    0.72
    ?”.
    0.68
    !".
    0.65
    !!.
    0.65
    !.
    0.64
    )”.
    0.64
    :.
    0.63
     &.
    0.63
    Activations Density 0.003%

    No Known Activations