© 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. 38099
    Prev
    Next
    INDEX
    Explanations

    Agda, Coq, license, Healthcare

    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
    .
    0.89
    ado
    0.81
     as
    0.76
    EM
    0.75
    ed
    0.71
    च
    0.70
    ą
    0.70
    WAR
    0.70
     waffle
    0.70
    "
    0.70
    POSITIVE LOGITS
    goers
    0.73
    й
    0.66
    jene
    0.63
    negie
    0.63
    जनन
    0.63
    Ⴖ
    0.63
     ভুট্টোর
    0.62
    cPix
    0.61
    kana
    0.60
     आठवीं
    0.60
    Activations Density 0.001%

    No Known Activations