© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175505
    Prev
    Next
    INDEX
    Explanations

    maximum iterations

    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_20_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
     тря
    0.42
     Да
    0.40
    ΤΟ
    0.40
     Persistent
    0.39
    膣
    0.39
     Ор
    0.39
     TFT
    0.39
     һ
    0.38
     persisted
    0.38
    ласти
    0.38
    POSITIVE LOGITS
     coordinador
    0.44
    r
    0.44
    ie
    0.44
    );
    0.43
    aspectj
    0.43
    cuador
    0.42
    ucing
    0.42
    rà
    0.42
     colombiano
    0.42
     outfielder
    0.41
    Activations Density 0.003%

    No Known Activations