© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237975
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_32_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
    िक्सल
    0.32
     refundable
    0.31
     sol
    0.30
     rogue
    0.30
     forgo
    0.30
    견
    0.30
     strata
    0.29
     poodle
    0.29
     QP
    0.29
     furl
    0.29
    POSITIVE LOGITS
     Verlauf
    0.31
     Dighe
    0.31
     الايه
    0.31
    ául
    0.30
    另一个
    0.30
    썻
    0.29
     ভিন্ন
    0.29
    Ante
    0.29
    стую
    0.29
    活动的
    0.29
    Activations Density 0.000%

    No Known Activations