© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198479
    Prev
    Next
    INDEX
    Explanations

    stop

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    elevationMap
    0.43
    ">=</
    0.43
    Straw
    0.42
    祅
    0.40
     Sutherland
    0.38
     Straw
    0.38
    Toyota
    0.38
    irer
    0.38
    图案
    0.38
    Suzuki
    0.38
    POSITIVE LOGITS
    停
    0.96
    停止
    0.82
     stopped
    0.75
     stopping
    0.75
     Stopped
    0.74
     stop
    0.73
    stopped
    0.71
     poz
    0.68
    STOP
    0.68
    Stopped
    0.68
    Activations Density 0.000%

    No Known Activations