© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166729
    Prev
    Next
    INDEX
    Explanations

    prostate function

    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_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
    sof
    0.45
    otyping
    0.42
    soff
    0.41
     $=$
    0.41
     $=\
    0.39
    intro
    0.39
    referer
    0.39
     требует
    0.39
     विवे
    0.38
    ۷
    0.38
    POSITIVE LOGITS
     powdered
    0.43
     KN
    0.42
     drizzle
    0.42
     Kn
    0.39
     kn
    0.39
     incoming
    0.38
     Artist
    0.37
    KN
    0.37
     समन्व
    0.37
     tact
    0.36
    Activations Density 0.010%

    No Known Activations