© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158841
    Prev
    Next
    INDEX
    Explanations

    promises, aromatics

    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_2_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
    a
    1.51
    i
    1.34
    '
    1.25
    ла
    1.16
    that
    1.12
    ي
    1.12
    af
    1.10
    {
    1.09
    दा
    0.99
    れる
    0.98
    POSITIVE LOGITS
    al
    1.14
    א
    1.13
    ש
    1.12
    O
    1.05
    র
    0.97
    お知らせ
    0.97
    ო
    0.97
    ית
    0.96
    ן
    0.91
    و
    0.90
    Activations Density 0.002%

    No Known Activations