© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25799
    Prev
    Next
    INDEX
    Explanations

    emoticons and :) ;) :D

    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_10_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
    ا
    0.38
    ן
    0.35
    erweise
    0.34
    ycor
    0.34
    에
    0.33
    كيف
    0.33
    ího
    0.33
     electrónica
    0.32
     effectués
    0.32
     prestig
    0.32
    POSITIVE LOGITS
    </h2>
    0.38
     that
    0.38
     $
    0.32
    well
    0.30
    ार
    0.30
    int
    0.30
    $
    0.30
    </u>
    0.29
     congruence
    0.29
     bloke
    0.29
    Activations Density 0.001%

    No Known Activations