© 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. 199048
    Prev
    Next
    INDEX
    Explanations

    hotter than

    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
    getCharAt
    0.17
     ۱۵
    0.17
    Ⴚ
    0.17
    ಯ್
    0.17
    </h2>
    0.15
    ｋ
    0.15
     ஆண்ட
    0.15
    થમ
    0.15
     இஸ்
    0.15
    ہرے
    0.15
    POSITIVE LOGITS
    as
    0.20
    t
    0.20
    ↵↵
    0.18
        
    0.17
     Leaving
    0.17
    ান
    0.17
     discount
    0.17
    甜蜜
    0.17
    ректор
    0.16
    www
    0.16
    Activations Density 0.001%

    No Known Activations