© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44518
    Prev
    Next
    INDEX
    Explanations

    roblox game development

    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
    2
    0.92
    ACT
    0.74
    Repository
    0.71
    DL
    0.68
    DNS
    0.68
    Data
    0.65
    GEN
    0.64
    FQ
    0.63
    Num
    0.63
    FE
    0.63
    POSITIVE LOGITS
    ра
    0.78
    า
    0.77
    as
    0.73
    س
    0.72
    in
    0.70
     are
    0.67
    os
    0.66
    inę
    0.65
     другом
    0.64
     been
    0.64
    Activations Density 0.003%

    No Known Activations