© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195146
    Prev
    Next
    INDEX
    Explanations

    one's

    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_4_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
    し
    1.17
    した
    1.05
    ва
    1.05
    ৫
    1.00
    ’
    0.99
    見える
    0.96
    見
    0.96
    ți
    0.95
    取り
    0.95
    я
    0.89
    POSITIVE LOGITS
    u
    1.31
    i
    1.07
    ו
    1.03
    m
    1.02
    to
    1.00
    at
    0.96
    songs
    0.94
    schools
    0.91
    ppies
    0.90
    {
    0.89
    Activations Density 0.001%

    No Known Activations