© 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. 126224
    Prev
    Next
    INDEX
    Explanations

    run, movement, runners

    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
     halfway
    0.41
    陥
    0.40
    ément
    0.38
    izza
    0.37
    เท้า
    0.37
    タッチ
    0.36
    hlen
    0.36
    篷
    0.35
    inhua
    0.35
     entlang
    0.34
    POSITIVE LOGITS
     runs
    0.71
    runs
    0.65
     Runs
    0.64
    Runs
    0.59
     run
    0.57
     움직
    0.50
     дви
    0.48
     movimenti
    0.47
     движения
    0.46
     руха
    0.46
    Activations Density 0.001%

    No Known Activations