© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170718
    Prev
    Next
    INDEX
    Explanations

    foreign script

    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_56_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
    $:
    0.40
    uità
    0.36
    Mys
    0.36
     Wynn
    0.35
    Having
    0.35
     друз
    0.35
     weiteren
    0.34
    ாள
    0.33
    ：
    0.33
     fio
    0.33
    POSITIVE LOGITS
    sty
    0.41
     गाया
    0.41
    MARKS
    0.41
    skom
    0.40
    охра
    0.39
    oty
    0.38
    পাড়
    0.37
     Ley
    0.37
    colgroup
    0.37
    сторон
    0.36
    Activations Density 0.000%

    No Known Activations