© 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. 221984
    Prev
    Next
    INDEX
    Explanations

    commands and special characters

    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
    ية
    0.78
    あ
    0.73
    ب
    0.71
    א
    0.71
    ৬
    0.69
    يب
    0.68
    an
    0.68
    ado
    0.68
    ال
    0.67
    ся
    0.67
    POSITIVE LOGITS
    ﻢ
    0.79
    2
    0.76
    ﺖ
    0.75
    3
    0.72
    BOOK
    0.70
    ОВ
    0.68
    ﻰ
    0.68
    ﻖ
    0.68
    ﻚ
    0.67
    ﺶ
    0.67
    Activations Density 0.000%

    No Known Activations