© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49409
    Prev
    Next
    INDEX
    Explanations

    author

    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
     власти
    0.42
    imaan
    0.38
    ike
    0.37
    rocin
    0.36
    ਭ
    0.36
    ウル
    0.35
    ïd
    0.35
    វេ
    0.34
     ஆட்சிய
    0.33
    నాల
    0.33
    POSITIVE LOGITS
     author
    3.83
    author
    3.42
    Author
    3.23
     Author
    3.20
     autor
    3.02
     автор
    3.00
    作者
    2.61
     AUTHOR
    2.59
     Автор
    2.53
    Автор
    2.34
    Activations Density 0.145%

    No Known Activations