© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66256
    Prev
    Next
    INDEX
    Explanations

    O

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     PAH
    0.41
    πα
    0.40
     FCS
    0.39
     ஹீ
    0.39
     TCS
    0.39
    વ
    0.39
     па
    0.38
     HEL
    0.38
    ocate
    0.38
    osaic
    0.38
    POSITIVE LOGITS
     zippered
    0.43
    Philipp
    0.41
    zz
    0.41
    zip
    0.40
    펜
    0.39
     vaz
    0.38
    ্যক
    0.38
    स्थापित
    0.38
    錯
    0.38
    angler
    0.37
    Activations Density 0.004%

    No Known Activations