© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38513
    Prev
    Next
    INDEX
    Explanations

    live events and sales channels

    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_3_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
    P
    0.95
     o
    0.78
    A
    0.77
    X
    0.71
     a
    0.70
    E
    0.69
    D
    0.69
    B
    0.66
     t
    0.65
    od
    0.65
    POSITIVE LOGITS
    اتی
    0.79
    の話
    0.77
    мами
    0.74
    لے
    0.72
    ти
    0.71
    ﻃ
    0.71
    ला
    0.70
    っており
    0.70
    धाम
    0.69
    ित्र
    0.67
    Activations Density 0.004%

    No Known Activations