© 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. 41043
    Prev
    Next
    INDEX
    Explanations

    file or part handling

    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
    ة
    0.91
    ing
    0.86
    ת
    0.78
    ле
    0.77
    us
    0.74
    ens
    0.73
    л
    0.72
    ä
    0.71
    is
    0.68
    ↵↵
    0.67
    POSITIVE LOGITS
    ك
    0.72
    .<
    0.70
     свое
    0.63
    gambar
    0.59
     modificaciones
    0.58
    fY
    0.58
     alteraciones
    0.57
    ₵
    0.57
    ક
    0.56
     attivo
    0.56
    Activations Density 0.015%

    No Known Activations