© 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. 151296
    Prev
    Next
    INDEX
    Explanations

    }</

    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
    many
    0.40
    ／
    0.38
    multipart
    0.38
     Version
    0.37
    benzoimidazol
    0.37
    addSubview
    0.37
    windowFixedWidth
    0.37
     Us
    0.36
    autoprefixer
    0.36
    strategies
    0.36
    POSITIVE LOGITS
    P
    0.49
    5
    0.48
    Close
    0.47
    Ante
    0.47
     file
    0.45
     function
    0.45
     std
    0.44
    Reve
    0.44
     becomes
    0.43
     wy
    0.43
    Activations Density 0.000%

    No Known Activations