© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92383
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     on
    0.54
    ко
    0.46
    в
    0.46
    В
    0.45
     also
    0.45
    й
    0.44
    ра
    0.43
    у
    0.43
    ме
    0.43
     tốt
    0.42
    POSITIVE LOGITS
    /
    0.80
    that
    0.57
     mutta
    0.53
    :
    0.53
    (
    0.51
     tetapi
    0.50
     щоб
    0.50
    in
    0.49
    whereas
    0.49
    :@"
    0.48
    Activations Density 0.000%

    No Known Activations