© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6844
    Prev
    Next
    INDEX
    Explanations

    ideas cost money

    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_39_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
     Wallis
    0.39
     Canadians
    0.37
     politicians
    0.36
     þei
    0.36
    الیا
    0.36
    bac
    0.35
     😄
    0.35
     Lippincott
    0.34
    ivers
    0.34
    astics
    0.34
    POSITIVE LOGITS
     상
    0.38
     biy
    0.38
     alguma
    0.36
     폐
    0.36
     పాఠ
    0.36
     pach
    0.36
    ㎿
    0.35
    )//
    0.35
     dezelfde
    0.35
     санк
    0.35
    Activations Density 0.000%

    No Known Activations