© 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
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40545
    Prev
    Next
    INDEX
    Explanations

    size

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     ㅅ
    0.42
    няка
    0.37
     ļ
    0.36
     ㅎ
    0.36
    ὲ
    0.35
    ㄸ
    0.35
    versible
    0.35
     />;
    0.34
    ᄄ
    0.34
     persönlich
    0.33
    POSITIVE LOGITS
    St
    0.50
    Ty
    0.44
    Famous
    0.41
    Update
    0.41
    Qu
    0.41
    Grey
    0.41
    Version
    0.40
    GNU
    0.40
    <tr>
    0.40
    Separate
    0.39
    Activations Density 0.001%

    No Known Activations