© 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. 29912
    Prev
    Next
    INDEX
    Explanations

    SET, sem, REM, BEC

    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
    en
    0.99
    s
    0.90
    inį
    0.89
    o
    0.89
    er
    0.88
    in
    0.85
    ä
    0.84
     entreg
    0.81
    ים
    0.80
     informa
    0.79
    POSITIVE LOGITS
     ਹ
    0.65
     ד
    0.64
     ಕ
    0.60
    }:
    0.60
     צ
    0.59
    H
    0.59
    lessly
    0.59
     ว
    0.58
    EY
    0.58
    da
    0.57
    Activations Density 0.029%

    No Known Activations