© 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. 201535
    Prev
    Next
    INDEX
    Explanations

    uck

    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
    カップ
    0.43
    淙
    0.37
     plank
    0.37
    resolvers
    0.37
    WEST
    0.37
    Overflow
    0.36
    acements
    0.35
    chips
    0.35
     resuelve
    0.35
    𒉈
    0.35
    POSITIVE LOGITS
    谄
    0.88
     flattering
    0.75
     flatter
    0.72
     flattered
    0.71
     sy
    0.67
    谀
    0.67
     suck
    0.61
     lick
    0.59
     sucking
    0.59
     subserv
    0.55
    Activations Density 0.002%

    No Known Activations