© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235619
    Prev
    Next
    INDEX
    Explanations

    list items, code, text

    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_32_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
    
    0.46
    也可以
    0.42
    Canon
    0.42
    Basel
    0.42
    đer
    0.40
     "));
    0.40
    CELL
    0.39
     Cancellation
    0.39
     ciekaw
    0.39
    CRET
    0.39
    POSITIVE LOGITS
     inequality
    0.41
     frust
    0.38
     merupakan
    0.38
     ngăn
    0.38
     vendre
    0.38
     rappro
    0.38
     lesz
    0.38
     largeur
    0.38
    publique
    0.37
    |^{-
    0.37
    Activations Density 0.004%

    No Known Activations