© 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. 159172
    Prev
    Next
    INDEX
    Explanations

    Vaporeon, VRM, Motherboard

    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
    но
    1.10
    ,
    1.02
    \
    0.95
    و
    0.93
    ת
    0.90
    am
    0.89
    د
    0.89
    ల
    0.88
    ２
    0.87
    toare
    0.82
    POSITIVE LOGITS
    il
    0.84
     I
    0.84
    ir
    0.82
    in
    0.82
    1
    0.81
     for
    0.76
    తో
    0.74
     a
    0.73
    ge
    0.71
     malicious
    0.71
    Activations Density 0.000%

    No Known Activations