© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131826
    Prev
    Next
    INDEX
    Explanations

    data collection methods

    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_6_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
    p
    1.37
    a
    1.33
    ul
    1.27
    u
    1.27
    in
    1.23
    ו
    1.16
    ings
    1.14
    In
    1.13
    as
    1.13
    n
    1.12
    POSITIVE LOGITS
    üd
    0.82
    )،
    0.80
    ли
    0.79
    räume
    0.79
    új
    0.77
    ración
    0.75
    чення
    0.75
    見える
    0.75
    িল্লি
    0.75
    '}}
    0.74
    Activations Density 0.001%

    No Known Activations