© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44264
    Prev
    Next
    INDEX
    Explanations

    low-code / low-carb

    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_3_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
    л
    0.87
    ات
    0.81
    ب
    0.78
    지
    0.77
    이었
    0.75
    މ
    0.73
    u
    0.71
    家
    0.71
    Autoresizing
    0.69
    owo
    0.68
    POSITIVE LOGITS
    PL
    0.63
    PLA
    0.62
    ことができる
    0.60
     in
    0.59
    TEM
    0.58
    POWER
    0.58
    U
    0.58
    quality
    0.55
    AS
    0.54
    RO
    0.54
    Activations Density 0.003%

    No Known Activations