© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204698
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_56_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
    Turning
    0.37
    瞻
    0.35
     turning
    0.34
    ющихся
    0.33
    ).^
    0.32
    __________
    0.32
     drops
    0.32
    রত
    0.32
    ক্ষণিক
    0.32
    тился
    0.31
    POSITIVE LOGITS
     child
    0.38
     йил
    0.36
     打
    0.35
     இவ்
    0.34
     trou
    0.33
     established
    0.33
     vuoden
    0.33
    饺
    0.33
    氵
    0.33
     airport
    0.32
    Activations Density 0.002%

    No Known Activations