© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25764
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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_10_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
    ни
    0.76
     T
    0.71
    𝐧
    0.70
     reinvest
    0.69
     pavatt
    0.68
    ี
    0.68
    ної
    0.66
     allocating
    0.65
     Valletta
    0.65
     возгла
    0.64
    POSITIVE LOGITS
    ق
    0.95
    F
    0.82
    H
    0.80
    G
    0.78
    ב
    0.75
    Gen
    0.74
    Simple
    0.73
    R
    0.73
    L
    0.73
    N
    0.73
    Activations Density 0.000%

    No Known Activations