© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197013
    Prev
    Next
    INDEX
    Explanations

    syllogism

    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_26_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
     ഈ
    0.49
     szak
    0.46
    ":[
    0.46
     savk
    0.46
     इवनिंग
    0.46
     ezek
    0.44
     ຫຼື
    0.43
     phénom
    0.43
     செயல்ப
    0.43
    ):["
    0.42
    POSITIVE LOGITS
     as
    0.42
    加
    0.42
     Calvary
    0.41
     Economies
    0.41
    al
    0.41
     Capitol
    0.39
    เขต
    0.39
    as
    0.38
    en
    0.38
     Ensure
    0.38
    Activations Density 0.000%

    No Known Activations