© 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. 110579
    Prev
    Next
    INDEX
    Explanations

    buffet

    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
    ру
    1.03
    ро
    0.97
     ότι
    0.97
    ра
    0.96
    .
    0.90
    न
    0.90
    up
    0.87
    ः
    0.87
    ני
    0.84
    ;
    0.83
    POSITIVE LOGITS
    s
    1.31
    ی
    1.30
    ים
    1.09
    0
    1.02
    ే
    0.96
    ség
    0.94
    g
    0.94
    ０
    0.92
    th
    0.89
    ﺕ
    0.89
    Activations Density 0.000%

    No Known Activations