© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50856
    Prev
    Next
    INDEX
    Explanations

    say "Maine"

    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_55_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
     अन
    0.45
    ાર
    0.38
     প্রতিবেদক
    0.38
     melan
    0.38
     Bugünkü
    0.38
    ímica
    0.38
    दून
    0.37
    芪
    0.37
    Pierce
    0.37
    머
    0.36
    POSITIVE LOGITS
    Turner
    0.45
     Turner
    0.44
    rs
    0.41
     Wald
    0.39
     Woodland
    0.38
    ASA
    0.37
     ক্লাশ
    0.36
     जंगल
    0.36
    CCNC
    0.35
     White
    0.35
    Activations Density 0.001%

    No Known Activations