© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257995
    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_22_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
    この
    0.46
     無
    0.45
     भेंट
    0.45
     israel
    0.44
    人気
    0.44
    ResponseEntity
    0.44
    ITIS
    0.43
    軗
    0.43
    ્યા
    0.43
    FH
    0.43
    POSITIVE LOGITS
     richtig
    0.54
    t
    0.46
    iere
    0.46
     richtigen
    0.45
     చిత్రం
    0.43
     Sicherheit
    0.42
     Lomond
    0.42
    lb
    0.41
     Warum
    0.41
     versuchen
    0.41
    Activations Density 0.000%

    No Known Activations