© 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. 86077
    Prev
    Next
    INDEX
    Explanations

    | Feature

    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
     [
    0.41
    0.41
     cela
    0.40
     IList
    0.39
     CDs
    0.39
     Psalms
    0.38
    ,[
    0.38
     When
    0.38
    ",
    0.37
     i
    0.37
    POSITIVE LOGITS
    ים
    0.48
    FEM
    0.45
     pathophys
    0.44
    lossen
    0.44
     fiery
    0.44
    ों
    0.43
    ického
    0.43
    yers
    0.43
    MovieModal
    0.42
    ஜித்
    0.42
    Activations Density 0.002%

    No Known Activations