© 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. 107593
    Prev
    Next
    INDEX
    Explanations

    worship after of

    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
    리
    1.72
    '
    1.63
    س
    1.59
    "
    1.52
    ス
    1.36
    ви
    1.31
    -
    1.29
    एस
    1.27
    ।
    1.21
    스의
    1.16
    POSITIVE LOGITS
    in
    1.16
    ak
    1.03
    이라
    0.96
     theses
    0.96
    이나
    0.96
    ین
    0.95
    ও
    0.95
    이라고
    0.93
     बढ़ावा
    0.91
    un
    0.91
    Activations Density 0.000%

    No Known Activations