© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76461
    Prev
    Next
    INDEX
    Explanations

    run-in, run-off, run-up

    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
    ого
    0.42
    John
    0.40
    Warren
    0.38
     JOHN
    0.38
    權
    0.36
    extreme
    0.35
     whitelist
    0.35
    RICH
    0.35
    granted
    0.35
    Leng
    0.35
    POSITIVE LOGITS
     রান
    0.42
     IOError
    0.42
    hny
    0.38
    簌
    0.38
     run
    0.38
     conflicts
    0.37
     Playoffs
    0.37
     பண்ட
    0.36
     décl
    0.36
     деб
    0.36
    Activations Density 0.006%

    No Known Activations