© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214651
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    u
    1.97
    in
    1.67
    as
    1.63
    er
    1.47
    o
    1.38
    at
    1.37
    of
    1.36
    id
    1.34
    an
    1.26
    e
    1.24
    POSITIVE LOGITS
    ча
    1.29
    жа
    1.14
    ক
    1.10
     アクセ
    1.09
    шна
    1.03
    горь
    1.00
    सी
    0.98
    жами
    0.98
    യും
    0.98
    টি
    0.97
    Activations Density 0.000%

    No Known Activations