© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163740
    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_31_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
    enamefont
    0.41
     StringVar
    0.40
     Leitung
    0.38
     клуб
    0.38
    વ
    0.38
     молеку
    0.37
     vaisse
    0.37
    ovalent
    0.37
     anga
    0.37
    shower
    0.37
    POSITIVE LOGITS
     एंट्री
    0.41
     sélectionner
    0.41
     Scanning
    0.38
    눠
    0.37
     CONDITIONS
    0.37
     totalité
    0.36
    FISH
    0.36
     scan
    0.36
    選
    0.36
     targets
    0.35
    Activations Density 0.000%

    No Known Activations