© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215764
    Prev
    Next
    INDEX
    Explanations

    Brier Score

    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_5_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
    。
    1.25
    ați
    1.08
    uje
    1.06
    '
    1.06
    DCTask
    1.02
    _
    1.00
    ).
    0.99
    აკ
    0.98
    ুকে
    0.96
     Verbrauch
    0.96
    POSITIVE LOGITS
    I
    1.47
    е
    1.42
    G
    1.30
    R
    1.30
    व
    1.30
    س
    1.24
    up
    1.19
    Y
    1.19
    S
    1.16
    se
    1.16
    Activations Density 0.000%

    No Known Activations