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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209216
    Prev
    Next
    INDEX
    Explanations

    ancient Greece

    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_20_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
     Trond
    0.42
     Idaho
    0.40
     defray
    0.40
     Haiti
    0.38
     anaemia
    0.38
     Norwegen
    0.38
     solcher
    0.37
    밝
    0.37
     Guam
    0.36
     Qué
    0.36
    POSITIVE LOGITS
    Carbon
    0.38
    كب
    0.35
     classic
    0.34
    Cour
    0.34
    Classic
    0.34
    ป
    0.33
    Swing
    0.33
    Canonical
    0.33
    Reilly
    0.33
    Qu
    0.32
    Activations Density 0.002%

    No Known Activations