© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231492
    Prev
    Next
    INDEX
    Explanations

    ISO 9001

    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_6_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
    ش
    1.30
    ल
    1.20
    ל
    1.15
    ص
    1.10
    ج
    1.05
    ס
    1.05
    ان
    1.01
    기
    0.98
    ಬ
    0.96
    Б
    0.96
    POSITIVE LOGITS
     of
    0.95
     not
    0.86
    וף
    0.82
     pulverized
    0.80
    чка
    0.79
     yapı
    0.79
     zoned
    0.76
     mined
    0.76
     steel
    0.75
     hız
    0.75
    Activations Density 0.001%

    No Known Activations