© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59309
    Prev
    Next
    INDEX
    Explanations

    c, p, l, or cy

    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
    ки
    0.83
    ้
    0.60
    도
    0.60
    for
    0.56
    ่
    0.55
    γ
    0.55
    هم
    0.54
    IS
    0.53
     определён
    0.53
    ει
    0.52
    POSITIVE LOGITS
    ﻤ
    0.59
    á
    0.57
    AT
    0.57
    st
    0.56
     weathered
    0.53
    ﺪ
    0.52
    LECTION
    0.51
    ﺘ
    0.51
    ﻜ
    0.51
    ATTER
    0.51
    Activations Density 0.000%

    No Known Activations