© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235057
    Prev
    Next
    INDEX
    Explanations

    failed functions

    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_32_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
    Cxt
    0.38
     turkish
    0.35
     وعلى
    0.34
    irsi
    0.34
    高品質
    0.34
    옻
    0.34
     سات
    0.34
    ordia
    0.34
    以下的
    0.34
     mineralization
    0.34
    POSITIVE LOGITS
    isho
    0.41
    )++;
    0.38
    ផ្ស
    0.37
    เรียก
    0.37
    শ্র
    0.36
    llam
    0.36
     downstairs
    0.35
     अमा
    0.34
     croy
    0.34
     لاب
    0.34
    Activations Density 0.001%

    No Known Activations