© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35939
    Prev
    Next
    INDEX
    Explanations

    company/provider services

    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_11_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
     مؤرشف
    0.56
     simplesmente
    0.56
     σε
    0.54
    ใจ
    0.53
    באנגלית
    0.52
    thisStudent
    0.51
    厛
    0.51
    遗憾
    0.50
    न्यूयॉर्क
    0.50
     רק
    0.50
    POSITIVE LOGITS
    er
    0.63
    id
    0.57
    ta
    0.57
     cadres
    0.57
    call
    0.56
    rich
    0.55
    ich
    0.53
    IE
    0.52
    褪
    0.52
    inity
    0.51
    Activations Density 0.024%

    No Known Activations