© 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. 253768
    Prev
    Next
    INDEX
    Explanations

    ob

    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
    ousand
    0.43
    étrica
    0.40
    Di
    0.37
    到
    0.36
    etted
    0.36
    igold
    0.36
    Ideally
    0.36
    oppos
    0.36
    ディ
    0.35
    ayan
    0.35
    POSITIVE LOGITS
     Spy
    0.41
    fares
    0.40
    нете
    0.39
    嶺
    0.39
     शेफाली
    0.39
     الشكل
    0.39
    ೖ
    0.37
     вас
    0.37
     Esto
    0.37
     बटे
    0.37
    Activations Density 0.000%

    No Known Activations