© 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. 27872
    Prev
    Next
    INDEX
    Explanations

    invalid input or JSON format

    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_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
     executes
    0.44
    executed
    0.38
     judged
    0.38
    >.
    0.37
     executing
    0.37
     ಭಾಗ
    0.37
     execute
    0.37
     gri
    0.37
     executed
    0.37
    autoconfigure
    0.37
    POSITIVE LOGITS
     caller
    0.45
    Calls
    0.45
     calls
    0.44
     Calls
    0.42
     modalCard
    0.41
     použit
    0.40
    CategoryID
    0.40
     Caller
    0.40
    款
    0.39
    Input
    0.39
    Activations Density 0.006%

    No Known Activations