© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138380
    Prev
    Next
    INDEX
    Explanations

    using System.Extensions

    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_37_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
     trivalent
    0.43
    icoli
    0.40
     triángulos
    0.38
    生理
    0.37
    reifen
    0.37
    肚
    0.37
    //#
    0.35
     clown
    0.35
    븐
    0.35
    sons
    0.35
    POSITIVE LOGITS
     Delegate
    0.44
    Delegate
    0.44
     Jamie
    0.43
    delegate
    0.43
     resolved
    0.41
     delegate
    0.41
     resolution
    0.40
     Resolved
    0.40
     logging
    0.39
     Logging
    0.39
    Activations Density 0.000%

    No Known Activations