© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159340
    Prev
    Next
    INDEX
    Explanations

    bat songs

    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
    ar
    1.45
    er
    1.37
    an
    1.30
    in
    1.22
    a
    1.17
    o
    1.17
    ر
    1.09
    ik
    0.92
    m
    0.92
     in
    0.91
    POSITIVE LOGITS
    ت
    1.13
    는
    1.10
    การ
    1.05
    は
    0.99
    ě
    0.97
    是
    0.95
     семь
    0.93
    ING
    0.91
    ِي
    0.86
    र्ने
    0.85
    Activations Density 0.000%

    No Known Activations