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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203832
    Prev
    Next
    INDEX
    Explanations

    steampowered.com

    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_6_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
    er
    1.77
    as
    1.76
    in
    1.70
    u
    1.70
    i
    1.68
    m
    1.54
    at
    1.39
    en
    1.34
    ed
    1.34
    h
    1.34
    POSITIVE LOGITS
     čís
    1.20
     ácido
    1.03
    ל
    1.02
    الن
    1.00
    نيا
    0.99
     завое
    0.98
     aște
    0.98
     ifade
    0.96
     يا
    0.95
     jähr
    0.95
    Activations Density 0.000%

    No Known Activations