© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108402
    Prev
    Next
    INDEX
    Explanations

    расскажи

    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_2_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
    s
    1.86
    ל
    1.46
    ল
    1.43
    (
    1.41
    \
    1.35
    ם
    1.33
    มี
    1.29
    ের
    1.24
    ר
    1.17
    ן
    1.11
    POSITIVE LOGITS
    ia
    1.09
    ik
    1.09
    iz
    1.08
    nosť
    1.04
    ih
    1.00
    어
    0.99
    ки
    0.97
     eléctricas
    0.96
    ла
    0.93
    ાળા
    0.93
    Activations Density 0.000%

    No Known Activations