© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78470
    Prev
    Next
    INDEX
    Explanations

    formulas with symbols and variables

    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_31_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
     ሃ
    0.29
     phyto
    0.29
    бто
    0.27
     انر
    0.27
     puan
    0.27
    embal
    0.26
    ウンド
    0.26
    γγελ
    0.26
    クール
    0.26
    냐
    0.26
    POSITIVE LOGITS
     Hooks
    0.30
    Литература
    0.29
     esfor
    0.27
     Andrea
    0.27
     Extensions
    0.27
    जनक
    0.27
     লবণ
    0.26
     Kep
    0.26
    kee
    0.25
     Influ
    0.25
    Activations Density 0.006%

    No Known Activations