© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221135
    Prev
    Next
    INDEX
    Explanations

    finally

    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_10_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
    ен
    0.76
    ený
    0.75
    嶆
    0.70
     Hör
    0.67
    ర్ణ
    0.67
    艾
    0.66
     Cols
    0.65
     mlijeka
    0.64
     întâ
    0.63
     Hendrick
    0.63
    POSITIVE LOGITS
    can
    0.95
    ان
    0.87
    व
    0.81
    ac
    0.77
    cz
    0.77
    ق
    0.76
    cs
    0.75
    ca
    0.74
    א
    0.73
    cb
    0.70
    Activations Density 0.001%

    No Known Activations