© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27611
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    觛
    0.39
     Unwrap
    0.38
    euler
    0.38
    HasStarred
    0.38
    osyl
    0.37
     mayonnaise
    0.36
     lovingly
    0.36
     पर्यायवाची
    0.35
     residency
    0.35
     unprotected
    0.35
    POSITIVE LOGITS
    usted
    0.47
    פן
    0.40
    iel
    0.38
    inko
    0.38
     recomendamos
    0.38
    采
    0.38
    Pct
    0.38
    recipient
    0.38
    ispielsweise
    0.38
     総
    0.37
    Activations Density 0.000%

    No Known Activations