© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81192
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming

    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_0_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
    他和
    1.45
     and
    1.38
    أ
    1.35
    我
    1.35
    B
    1.34
    U
    1.33
    M
    1.29
    他不
    1.28
    F
    1.27
    ？
    1.27
    POSITIVE LOGITS
    dır
    1.95
    .
    1.87
    '
    1.44
    ’
    1.39
    um
    1.35
    ной
    1.35
    ק
    1.30
    ิ
    1.25
     cornice
    1.23
    ร
    1.23
    Activations Density 0.032%

    No Known Activations