© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65337
    Prev
    Next
    INDEX
    Explanations

    set the stage

    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_41_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
    谔
    0.41
     switched
    0.39
     aportar
    0.38
     fathom
    0.38
     dawn
    0.38
     evolved
    0.37
     HIT
    0.37
    塔
    0.37
     yol
    0.37
     set
    0.36
    POSITIVE LOGITS
     stage
    1.75
    stage
    1.55
    Stage
    1.52
     Stage
    1.44
    舞台
    1.38
     स्टेज
    1.36
    STAGE
    1.26
    ステージ
    1.16
     stages
    1.13
     مرحله
    1.10
    Activations Density 0.003%

    No Known Activations