© 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. 28649
    Prev
    Next
    INDEX
    Explanations

    SIMD, NEON, Extensions

    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
    u
    0.86
     시장
    0.82
     spectrum
    0.80
     venden
    0.78
    Spectrum
    0.76
     Japón
    0.76
    。)
    0.75
    ۰
    0.74
    ཎ
    0.74
     phát
    0.73
    POSITIVE LOGITS
    anse
    0.87
    ash
    0.86
    na
    0.86
    ,
    0.84
    0.82
    .
    0.81
    є
    0.79
    ays
    0.79
    aya
    0.79
    ola
    0.77
    Activations Density 0.005%

    No Known Activations