© 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
    2. Gemma-3-27B-IT
    3. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 232807
    Prev
    Next
    INDEX
    Explanations

    using digital tools and infrastructure

    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_32_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
    José
    0.35
    鮑
    0.33
    Saxon
    0.33
    Jose
    0.32
     jose
    0.32
     रक्
    0.32
     Jose
    0.32
    เลือด
    0.31
    불
    0.31
    Suppl
    0.31
    POSITIVE LOGITS
    GeneratedValue
    0.31
    与其他
    0.31
    lea
    0.30
     дос
    0.29
     pouv
    0.29
     Goddard
    0.28
     predictive
    0.28
    apanicolaou
    0.28
     jumpa
    0.28
    beste
    0.28
    Activations Density 0.002%

    No Known Activations