© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33776
    Prev
    Next
    INDEX
    Explanations

    read on

    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
    2
    0.95
    *
    0.71
    ﺩ
    0.70
    ird
    0.69
    0.67
    -
    0.66
     device
    0.65
    ﻭ
    0.65
    .
    0.64
     backdoor
    0.63
    POSITIVE LOGITS
    at
    0.98
     are
    0.97
    inins
    0.94
    ే
    0.94
    in
    0.93
    atot
    0.92
    ா
    0.91
    tweets
    0.88
    ە
    0.88
    as
    0.87
    Activations Density 0.000%

    No Known Activations