© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44867
    Prev
    Next
    INDEX
    Explanations

    OpenAI-compatible API, resistant, girl, feta, data, magic

    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_22_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
     Infectious
    0.30
    гают
    0.29
     ಭಾಗ
    0.29
     आस्ट्रेलिया
    0.29
    鬏
    0.29
     அதன்
    0.28
     महत्त्वा
    0.28
     आईसी
    0.28
    튬
    0.28
    たない
    0.28
    POSITIVE LOGITS
    Line
    0.30
    Soph
    0.29
    mpg
    0.29
    zem
    0.28
    Geschichte
    0.28
    Inline
    0.27
    Market
    0.27
    line
    0.27
    vand
    0.26
    ben
    0.26
    Activations Density 0.053%

    No Known Activations