© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210902
    Prev
    Next
    INDEX
    Explanations

    em esse contexto

    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_5_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
    1.45
    ม
    1.39
    ž
    1.34
    ль
    1.24
    na
    1.16
     is
    1.15
    να
    1.14
    트
    1.13
    ला
    1.12
    ต
    1.11
    POSITIVE LOGITS
    ىرى
    1.13
    ى
    1.13
    us
    1.09
    )\
    1.05
     énon
    1.03
     می‌کن
    1.02
    ént
    0.99
    k
    0.98
    igkeiten
    0.98
    ’)
    0.96
    Activations Density 0.000%

    No Known Activations