© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60129
    Prev
    Next
    INDEX
    Explanations

    mixed scripts and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ²
    0.47
    º
    0.46
    ±
    0.45
    є
    0.44
    ¿
    0.42
    І
    0.42
    ¼
    0.42
     Р
    0.42
     баш
    0.41
     star
    0.41
    POSITIVE LOGITS
     „
    0.44
    „
    0.44
    []);
    0.36
    CREATED
    0.36
    CONFIGURATION
    0.36
    GW
    0.35
    govt
    0.35
     দ্বার
    0.35
     BREED
    0.35
    鍛
    0.34
    Activations Density 0.002%

    No Known Activations