© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195045
    Prev
    Next
    INDEX
    Explanations

    Chinese and Vietnamese names

    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_9_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
     Сан
    0.31
    1
    0.31
     Estadística
    0.31
    водства
    0.31
    ników
    0.30
     Zeichen
    0.29
     Initiatives
    0.28
     Dhawan
    0.28
    gies
    0.28
    До
    0.27
    POSITIVE LOGITS
     can
    0.36
     has
    0.34
    ก
    0.34
     scoff
    0.33
    0.33
     in
    0.31
     may
    0.31
     cannot
    0.31
    е
    0.30
     black
    0.30
    Activations Density 0.000%

    No Known Activations