© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31241
    Prev
    Next
    INDEX
    Explanations

    Begin followed by exclamation mark

    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_40_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
    small
    0.40
    ෝජ
    0.37
     кү
    0.36
     scre
    0.36
     सर्ट
    0.35
     сертифика
    0.35
    }|^
    0.35
    therapeutic
    0.35
    últ
    0.35
    ))^
    0.35
    POSITIVE LOGITS
     цикл
    0.50
    循环
    0.45
     cycle
    0.44
     цик
    0.42
    Ᏼ
    0.42
     цикла
    0.42
     Cycle
    0.41
     চক্র
    0.40
     चक्र
    0.40
    Cycle
    0.40
    Activations Density 0.002%

    No Known Activations