© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142754
    Prev
    Next
    INDEX
    Explanations

    police and celebrations

    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_0_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
    に
    1.45
     причин
    1.32
    ການ
    1.20
     ánimo
    1.20
     ľudí
    1.20
     razy
    1.19
    መት
    1.18
     notificación
    1.18
    귿
    1.18
     quei
    1.17
    POSITIVE LOGITS
    م
    2.28
    ب
    2.05
    و
    1.95
    g
    1.90
    د
    1.90
    v
    1.80
    p
    1.80
    of
    1.77
    ก
    1.71
    se
    1.70
    Activations Density 0.000%

    No Known Activations