© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9736
    Prev
    Next
    INDEX
    Explanations

    author/authors in citations

    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_40_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
     controlar
    0.39
    Citation
    0.38
    MATH
    0.38
     tratamento
    0.38
    升
    0.38
     احتاج
    0.37
    काना
    0.37
    MathML
    0.37
    玛
    0.36
    𒈥
    0.36
    POSITIVE LOGITS
     corporate
    0.59
    corporate
    0.54
     Corporate
    0.51
     CORPOR
    0.49
    Corporate
    0.48
     корпора
    0.48
     corpor
    0.45
     bump
    0.43
    bump
    0.42
     Hubbard
    0.41
    Activations Density 0.003%

    No Known Activations