© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13747
    Prev
    Next
    INDEX
    Explanations

    Russian Ministry and Federation

    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_13_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
    DOM
    0.55
     where
    0.48
    कांची
    0.47
    Č
    0.47
    ano
    0.47
    msk
    0.47
    אן
    0.46
    MCC
    0.46
    ELTS
    0.46
    羡
    0.46
    POSITIVE LOGITS
     Japanese
    0.57
    ૢ
    0.53
    顗
    0.52
     दोग
    0.51
     Ouais
    0.51
     دوس
    0.50
     세제곱
    0.49
     ձ
    0.49
    艸
    0.47
     vont
    0.47
    Activations Density 0.000%

    No Known Activations