© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199659
    Prev
    Next
    INDEX
    Explanations

    For a, For in, For air

    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_27_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
     optimised
    0.37
     gacche
    0.36
    лесо
    0.36
    кі
    0.35
    гүнкү
    0.35
    gql
    0.34
    Gruntfile
    0.34
    ሂ
    0.34
    tikz
    0.33
    ңы
    0.33
    POSITIVE LOGITS
     تتع
    0.37
     r
    0.34
     what
    0.33
     ر
    0.33
     Eul
    0.33
     Juan
    0.32
     Pr
    0.31
     فال
    0.31
     Fins
    0.30
     Urbana
    0.30
    Activations Density 0.001%

    No Known Activations