© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51100
    Prev
    Next
    INDEX
    Explanations

    phone number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    an
    0.59
    ви
    0.57
    that
    0.52
     Ä
    0.49
    ন
    0.49
    ש
    0.49
    ان
    0.48
    stranded
    0.48
    си
    0.46
    am
    0.45
    POSITIVE LOGITS
     percentile
    0.54
     constat
    0.52
    ewel
    0.45
     følge
    0.44
    ctions
    0.43
    e
    0.43
    o
    0.43
    ेंद्र
    0.43
    频繁
    0.43
     proficiency
    0.42
    Activations Density 0.004%

    No Known Activations