© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14581
    Prev
    Next
    INDEX
    Explanations

    honors, award, or complicated context

    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_15_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
    ėti
    0.41
    ów
    0.40
     നേതൃ
    0.39
     políticos
    0.38
    sized
    0.38
     வகையில்
    0.38
     回転
    0.37
     \%
    0.37
     சற்று
    0.37
    coons
    0.36
    POSITIVE LOGITS
    Calculator
    0.41
    婺
    0.41
    Anagram
    0.39
    Generate
    0.39
    تور
    0.38
     tombol
    0.38
    버
    0.38
    Color
    0.38
    Generator
    0.37
    (
    0.37
    Activations Density 0.007%

    No Known Activations