© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38407
    Prev
    Next
    INDEX
    Explanations

    double tap

    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_3_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
    ง
    0.75
    0.70
    ing
    0.59
     restless
    0.54
    ED
    0.54
    ですので
    0.54
    ）,
    0.53
    PE
    0.53
    ة
    0.53
     dilated
    0.52
    POSITIVE LOGITS
    ו
    0.87
    u
    0.73
    و
    0.71
    vention
    0.65
    𝙣
    0.62
    czki
    0.61
    其他
    0.60
    hension
    0.60
    cent
    0.59
    kowe
    0.59
    Activations Density 0.016%

    No Known Activations