© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89978
    Prev
    Next
    INDEX
    Explanations

    big companies and giants

    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_18_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
    
    0.33
    <0x19>
    0.32
     Zamora
    0.31
    썼
    0.31
     condense
    0.31
     వీరి
    0.31
     portefeuille
    0.31
    రావు
    0.30
    AppBsky
    0.30
    硯
    0.30
    POSITIVE LOGITS
    attempt
    0.30
    ualitas
    0.29
    ason
    0.28
     periodic
    0.27
     pokuš
    0.27
    ativa
    0.26
    nun
    0.26
     attempting
    0.26
    irth
    0.26
     mengucapkan
    0.26
    Activations Density 0.007%

    No Known Activations