© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83473
    Prev
    Next
    INDEX
    Explanations

    свод, vast

    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
    ه
    2.28
    া
    2.02
    ী
    1.97
    ;
    1.91
    :
    1.90
    ה
    1.90
    ین
    1.79
    )
    1.77
    ו
    1.73
    ться
    1.73
    POSITIVE LOGITS
    v
    1.61
    ne
    1.56
    c
    1.55
    ly
    1.42
    al
    1.37
    ها
    1.27
    h
    1.21
    um
    1.18
    om
    1.16
    f
    1.16
    Activations Density 0.000%

    No Known Activations