© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10181
    Prev
    Next
    INDEX
    Explanations

    xml document structure

    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_40_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
     Koles
    0.40
    㳑
    0.39
    Dept
    0.39
    Daw
    0.39
    Telemetry
    0.39
    িল্লি
    0.38
     Della
    0.38
     sâu
    0.37
     Radi
    0.36
    Ha
    0.36
    POSITIVE LOGITS
    堅持
    0.40
     підви
    0.40
     gespre
    0.38
    經
    0.38
     економі
    0.38
    econom
    0.37
     impractical
    0.37
     FRANCIS
    0.36
     поднима
    0.36
     conversa
    0.36
    Activations Density 0.000%

    No Known Activations