© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142532
    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_0_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
     Oracle
    0.54
    다
    0.53
     Sustain
    0.49
    to
    0.48
     thiab
    0.47
    يق
    0.47
     Ubuntu
    0.46
     Ausstattung
    0.46
     Owner
    0.45
     Pharmaceutical
    0.45
    POSITIVE LOGITS
    attered
    0.50
     attén
    0.50
    ン
    0.49
     ندرس
    0.49
    ಟರ್
    0.48
    峯
    0.48
     osserv
    0.48
    enne
    0.47
    ovan
    0.47
    TI
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.