© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 176751
    Prev
    Next
    INDEX
    Explanations

    @Entity public class

    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
    Negative Logits
     it
    0.46
     when
    0.45
    वहीं
    0.42
     meanwhile
    0.41
    સ્ક
    0.41
     επίσης
    0.41
    同樣
    0.41
     similarly
    0.40
     having
    0.40
    当
    0.40
    POSITIVE LOGITS
     abaste
    0.46
    !;
    0.45
    !';
    0.45
     Banquet
    0.45
    !";
    0.44
    FName
    0.44
    !"));
    0.43
     kí
    0.42
    /';
    0.41
    łącznie
    0.41
    Activations Density 0.000%

    No Known Activations