© 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. 42308
    Prev
    Next
    INDEX
    Explanations

    XML documentation comments

    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
    _{\
    0.41
    (%
    0.41
    助手
    0.40
    npm
    0.40
    
    0.39
    …。
    0.39
    する必要があります
    0.39
    Miche
    0.38
     UNI
    0.38
    ⑵
    0.38
    POSITIVE LOGITS
     terl
    0.41
    ક્તિ
    0.41
     stairs
    0.41
    órico
    0.41
    ্পনিক
    0.41
    owanych
    0.40
     approves
    0.39
     rápidos
    0.39
     berisi
    0.39
    ılması
    0.39
    Activations Density 0.002%

    No Known Activations