© 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. 43457
    Prev
    Next
    INDEX
    Explanations

    crosswalks, crosswinds, join

    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
    ਰ
    0.78
    v
    0.75
    ส
    0.73
    งาน
    0.63
    м
    0.63
    ک
    0.62
    સ
    0.59
    ا
    0.59
    \{
    0.58
    อื่น
    0.58
    POSITIVE LOGITS
    s
    0.95
    takes
    0.73
    يك
    0.71
    િ
    0.71
    take
    0.70
    人
    0.70
    ේ
    0.70
     crossover
    0.68
    iteľ
    0.67
     faintly
    0.66
    Activations Density 0.004%

    No Known Activations