© 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. 24129
    Prev
    Next
    INDEX
    Explanations

    lists of numbers

    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
     Fourteen
    0.36
    Eleven
    0.32
    šta
    0.32
     অনুরূপ
    0.32
     Seventy
    0.32
     re
    0.31
    യാണ
    0.30
    ◃
    0.30
     cảnh
    0.30
     sixteen
    0.30
    POSITIVE LOGITS
    !;
    0.31
     وغيرها
    0.31
    etc
    0.30
     Verfü
    0.29
    ]++;
    0.29
     तत्व
    0.28
     Disponible
    0.28
     Agenda
    0.28
    附加
    0.28
     Чу
    0.28
    Activations Density 0.007%

    No Known Activations