© 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. 5929
    Prev
    Next
    INDEX
    Explanations

    given limit or n

    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
    omitem
    0.39
     consumes
    0.38
     kisses
    0.38
     mys
    0.37
     dwells
    0.37
     Asiatic
    0.36
    aná
    0.36
    盟
    0.35
    ಲಿ
    0.35
     awa
    0.35
    POSITIVE LOGITS
     input
    0.37
     الداله
    0.36
    入力
    0.36
    льника
    0.35
     छोटे
    0.35
     Ero
    0.34
    输入
    0.34
    yip
    0.34
     nhỏ
    0.34
     Filho
    0.33
    Activations Density 0.031%

    No Known Activations