© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199591
    Prev
    Next
    INDEX
    Explanations

    Tactical / Stealth characters

    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_12_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
     clases
    0.49
    ग्ध
    0.46
    headings
    0.46
    ቋ
    0.46
    ellipse
    0.45
    arati
    0.45
    評價
    0.45
    foils
    0.45
     کیا۔
    0.44
     pavilions
    0.44
    POSITIVE LOGITS
    ందే
    0.50
     उन्हें
    0.49
    ガ
    0.48
     வாழைப்பழ
    0.48
     같습니다
    0.48
    amic
    0.47
     Qua
    0.47
    ними
    0.47
     =-
    0.47
     মা
    0.46
    Activations Density 0.000%

    No Known Activations