© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59727
    Prev
    Next
    INDEX
    Explanations

    stark

    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
     that
    1.61
    い
    1.39
    א
    1.39
    ী
    1.36
    는
    1.36
    ą
    1.34
    ı
    1.23
     you
    1.20
    is
    1.17
    は
    1.16
    POSITIVE LOGITS
     for
    1.29
    بة
    1.02
    تها
    0.97
    的大
    0.96
    在
    0.95
    情节
    0.94
    for
    0.94
    ولة
    0.93
    不
    0.93
    t
    0.92
    Activations Density 0.000%

    No Known Activations