© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5707
    Prev
    Next
    INDEX
    Explanations

    Tokyo, Toast, Tolkien

    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_38_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
     means
    0.46
     Means
    0.44
    󠁿
    0.39
    ivam
    0.38
     "|"
    0.37
     MEANS
    0.37
    ໌
    0.36
    꽂
    0.36
     쌍
    0.36
    Means
    0.35
    POSITIVE LOGITS
     ટો
    0.56
    โท
    0.51
    Toc
    0.47
     トー
    0.47
     टो
    0.46
    Tob
    0.46
    чной
    0.45
    টো
    0.45
    kyo
    0.45
     Tó
    0.44
    Activations Density 0.161%

    No Known Activations