© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239020
    Prev
    Next
    INDEX
    Explanations

    EndeavourOS, Trip, Ia, fork

    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_25_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
    诸
    0.30
     terpenes
    0.29
    (`/
    0.29
     rodents
    0.28
    ossus
    0.27
    諸
    0.27
    स्या
    0.26
    व्यक्तित्व
    0.26
    matically
    0.26
     টিক্কা
    0.26
    POSITIVE LOGITS
     i
    0.30
     и
    0.28
     و
    0.27
     roz
    0.26
     "";
    0.26
     mais
    0.26
     biv
    0.25
     questo
    0.25
    mathrm
    0.25
     trasform
    0.25
    Activations Density 0.000%

    No Known Activations