© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85693
    Prev
    Next
    INDEX
    Explanations

    muttering to himself

    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_18_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
     harboring
    0.53
     Congr
    0.50
     recommandée
    0.47
     Onder
    0.46
     réellement
    0.45
     oliva
    0.45
     ¬
    0.44
     AH
    0.44
    啰
    0.44
     comenzaron
    0.44
    POSITIVE LOGITS
    shan
    0.48
    シャツ
    0.46
    Shan
    0.46
     শাম
    0.46
     memes
    0.45
    碌
    0.45
    க்கான
    0.45
    ដូច
    0.44
     সাম
    0.43
     foodstuffs
    0.43
    Activations Density 0.002%

    No Known Activations