© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7620
    Prev
    Next
    INDEX
    Explanations

    local service agency

    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
     trig
    0.39
    साब
    0.38
     cann
    0.38
     indicador
    0.37
     attractor
    0.36
     ओपी
    0.36
    墨西哥
    0.35
    玺
    0.35
     indicadores
    0.35
     العلام
    0.35
    POSITIVE LOGITS
     agency
    1.67
     agencies
    1.63
     Agencies
    1.52
    Agency
    1.47
    agency
    1.46
     Agency
    1.45
     AGENCY
    1.34
     एजेंसी
    1.28
     agencia
    1.27
     एजेंसियों
    1.21
    Activations Density 0.061%

    No Known Activations