© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63680
    Prev
    Next
    INDEX
    Explanations

    figure

    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_59_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
    /
    0.60
    ／
    0.47
    sections
    0.46
    Like
    0.45
    functions
    0.45
    master
    0.44
    section
    0.42
     ／
    0.42
    work
    0.42
     s
    0.41
    POSITIVE LOGITS
    தி
    0.39
    та
    0.38
     नये
    0.38
    ы
    0.38
     Biographical
    0.38
     Most
    0.37
     marvellous
    0.37
    تی
    0.37
     nouvelle
    0.36
     Smaller
    0.36
    Activations Density 0.000%

    No Known Activations