© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93374
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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_60_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
     Solving
    0.39
     Shy
    0.39
    ْنَ
    0.38
    _;
    0.38
     Spending
    0.37
    Sz
    0.36
    ٥
    0.36
     fifty
    0.36
     ۵
    0.36
    νος
    0.35
    POSITIVE LOGITS
     stepper
    0.41
     array
    0.40
    '"
    0.39
     accelerometer
    0.38
    ",
    0.38
    "${
    0.37
     lumen
    0.36
    ’
    0.36
     scraper
    0.35
     corset
    0.35
    Activations Density 0.002%

    No Known Activations