© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30732
    Prev
    Next
    INDEX
    Explanations

    validations, quantizations, precisions

    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_7_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
    ’
    0.72
    for
    0.69
     Advis
    0.69
    rst
    0.59
     applic
    0.59
    l
    0.59
     avoir
    0.58
    sst
    0.58
     afficher
    0.58
     for
    0.58
    POSITIVE LOGITS
    os
    0.89
    с
    0.84
    는
    0.74
    ה
    0.73
    로
    0.72
    は
    0.71
    Waar
    0.64
    ס
    0.64
    ın
    0.63
    as
    0.62
    Activations Density 0.015%

    No Known Activations