© 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. 197029
    Prev
    Next
    INDEX
    Explanations

    pages/ followed by path

    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
     ถ้า
    0.38
    誊
    0.38
    还没有
    0.37
     liberation
    0.37
     beiden
    0.37
     دونوں
    0.37
    ค
    0.37
     သိ
    0.36
    ूथ
    0.36
     것을
    0.36
    POSITIVE LOGITS
    ulos
    0.42
    iku
    0.41
     consegn
    0.39
    aths
    0.38
    barrel
    0.38
    逐
    0.38
    aze
    0.37
     工作
    0.37
     mwen
    0.37
    SEC
    0.37
    Activations Density 0.001%

    No Known Activations