© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234903
    Prev
    Next
    INDEX
    Explanations

    universities and institutions

    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_32_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
     উত
    0.37
     credits
    0.37
    پیگنڈ
    0.36
    棗
    0.36
     credited
    0.34
     trigger
    0.34
     empate
    0.34
     contributo
    0.34
    ForResult
    0.34
    ૨
    0.34
    POSITIVE LOGITS
     stoves
    0.39
    ceans
    0.37
    ন্যার
    0.37
    일을
    0.37
    ครัว
    0.36
     Suburban
    0.36
     trainees
    0.35
     మార
    0.35
    zad
    0.35
    mesinin
    0.35
    Activations Density 0.001%

    No Known Activations