© 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. 32763
    Prev
    Next
    INDEX
    Explanations

    code writing and related tasks

    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
    πομπ
    0.37
     triun
    0.37
    Translator
    0.37
    купа
    0.36
     শাসক
    0.36
    ابعه
    0.35
     титу
    0.35
    墀
    0.35
    □
    0.34
     الصفحه
    0.34
    POSITIVE LOGITS
    atts
    0.37
    atural
    0.37
    items
    0.35
    fields
    0.33
     zaidi
    0.33
    itens
    0.33
    きゃ
    0.32
     शह
    0.32
     entier
    0.32
     كامل
    0.32
    Activations Density 0.033%

    No Known Activations