© 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. 31210
    Prev
    Next
    INDEX
    Explanations

    looking up, for, at, or over

    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
     useAppContext
    0.48
    assertTrue
    0.45
    াবণ
    0.43
    celli
    0.41
     Shams
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
     부정
    0.38
     안정
    0.37
    klar
    0.37
    albeit
    0.37
    POSITIVE LOGITS
     LOOK
    0.60
     Look
    0.57
     Looking
    0.57
     looking
    0.55
    看向
    0.54
     look
    0.53
     Looks
    0.52
     gazing
    0.52
    Look
    0.50
     looks
    0.50
    Activations Density 0.003%

    No Known Activations