© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123314
    Prev
    Next
    INDEX
    Explanations

    area of interest

    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_3_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
    h
    0.85
    areas
    0.80
    ders
    0.71
    sectors
    0.71
    area
    0.71
     AREA
    0.69
     Areas
    0.68
    rors
    0.64
    AREA
    0.63
    vt
    0.63
    POSITIVE LOGITS
    ä
    0.88
    시
    0.86
    어
    0.84
    로
    0.81
    ב
    0.79
     categor
    0.77
    은
    0.77
    ü
    0.77
    に行
    0.75
     $
    0.74
    Activations Density 0.003%

    No Known Activations