© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9195
    Prev
    Next
    INDEX
    Explanations

    struct definition

    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_13_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
    ස්ට
    0.51
    奂
    0.50
    ියා
    0.49
    лся
    0.49
    쭉
    0.48
     aga
    0.48
    ыска
    0.48
    යට
    0.48
    лыми
    0.48
     desarroll
    0.47
    POSITIVE LOGITS
    essing
    0.52
     CHROM
    0.51
    oo
    0.50
     ،
    0.49
    <start_of_image>
    0.49
     PRIV
    0.48
     ，
    0.47
    it
    0.47
     Permissions
    0.46
    oi
    0.46
    Activations Density 0.037%

    No Known Activations