© 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. 210136
    Prev
    Next
    INDEX
    Explanations

    as well

    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
    вів
    0.85
    скае
    0.79
     மணியே
    0.72
    ลีก
    0.72
    椹
    0.72
    ()==
    0.71
    ﻓ
    0.71
    あり
    0.71
    вами
    0.71
    ΙΚ
    0.70
    POSITIVE LOGITS
     to
    1.37
    to
    1.30
     an
    1.23
    s
    1.23
    IC
    1.01
    K
    1.01
     on
    1.00
    AC
    0.95
    J
    0.94
    L
    0.93
    Activations Density 0.002%

    No Known Activations