© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107981
    Prev
    Next
    INDEX
    Explanations

    child, build, wild, guild, bewildered

    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_1_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
     в
    1.45
     في
    1.27
     in
    1.09
    다
    1.08
     σε
    1.07
     در
    1.06
    P
    1.02
     recognized
    0.98
    ties
    0.97
    ção
    0.96
    POSITIVE LOGITS
    ig
    1.26
    ص
    1.23
    ن
    1.22
    بود
    1.05
    ник
    1.04
    عمل
    1.04
    اج
    1.03
     GSi
    1.03
    ל
    1.02
     Scri
    1.02
    Activations Density 0.000%

    No Known Activations