© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109095
    Prev
    Next
    INDEX
    Explanations

    el centro

    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_1_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
    t
    1.56
    т
    1.24
    u
    1.20
    ت
    1.18
    y
    1.17
    ו
    1.03
    There
    0.86
    an
    0.86
    at
    0.84
    IAN
    0.80
    POSITIVE LOGITS
    し
    1.21
    ме
    1.12
    те
    1.04
    ोट
    0.99
    ک
    0.98
    ่
    0.98
    お願い
    0.96
    ες
    0.96
    ει
    0.95
    grader
    0.95
    Activations Density 0.001%

    No Known Activations