© 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. 209404
    Prev
    Next
    INDEX
    Explanations

    grey beard, dust, vortex, void, whiskers

    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
     antioxidant
    0.32
    ท
    0.31
    Архі
    0.30
        
    0.30
    ใน
    0.30
    ทั้งหมด
    0.29
    ílio
    0.29
    -
    0.29
    นา
    0.28
    นาด
    0.27
    POSITIVE LOGITS
    is
    0.44
    r
    0.35
    ك
    0.34
    if
    0.32
    ğa
    0.32
    isn
    0.31
     šta
    0.31
    iop
    0.31
    oi
    0.30
    azzo
    0.30
    Activations Density 0.003%

    No Known Activations