© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198184
    Prev
    Next
    INDEX
    Explanations

    def

    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_27_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
    DIA
    0.39
     самые
    0.37
    дила
    0.37
    较高
    0.36
     ε
    0.36
    喜
    0.36
    ларда
    0.35
    viral
    0.34
    ເທ
    0.34
    高
    0.34
    POSITIVE LOGITS
    ionage
    0.38
    ųjų
    0.37
     dishonesty
    0.36
     Outstanding
    0.35
     rotten
    0.35
     administration
    0.35
     bouncing
    0.34
     Kollegen
    0.33
     negligence
    0.33
     Rolling
    0.33
    Activations Density 0.002%

    No Known Activations