© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24815
    Prev
    Next
    INDEX
    Explanations

    situational definition, theories, Harvey

    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_10_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
     interlocking
    0.23
     metamorphic
    0.23
     estimations
    0.23
     протяжении
    0.22
     thermoplastic
    0.22
    行情
    0.21
     plank
    0.21
    禕
    0.20
     milliam
    0.20
     rotting
    0.20
    POSITIVE LOGITS
     Hemos
    0.27
    ad
    0.25
    يء
    0.24
     Algunos
    0.24
    щи
    0.23
     می‌ده
    0.23
    u
    0.23
     Swinging
    0.22
    juč
    0.22
    Hilo
    0.22
    Activations Density 0.093%

    No Known Activations