© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133012
    Prev
    Next
    INDEX
    Explanations

    Champlain and Prolog

    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_6_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
    ä
    1.11
    ii
    1.09
    ش
    1.08
    ى
    1.08
    iet
    1.03
    ።
    1.03
    et
    0.95
    ill
    0.95
    ení
    0.93
    rí
    0.93
    POSITIVE LOGITS
    IN
    1.23
    AL
    1.11
    Y
    1.02
    Aqui
    0.97
    म
    0.96
    ו
    0.95
    IA
    0.93
    Ag
    0.93
    Q
    0.92
    เขา
    0.90
    Activations Density 0.000%

    No Known Activations