© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48797
    Prev
    Next
    INDEX
    Explanations

    expose

    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_10_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
    ir
    0.55
    1
    0.53
    im
    0.52
    ad
    0.49
    ang
    0.49
    nin
    0.43
    K
    0.43
    ப்படம்
    0.41
     chwili
    0.41
     قیام
    0.41
    POSITIVE LOGITS
    ات
    0.42
     authored
    0.42
    う
    0.41
    тра
    0.41
    ³.
    0.41
     mutex
    0.40
    ു
    0.40
    㪇
    0.38
     مِن
    0.38
    ث
    0.38
    Activations Density 0.006%

    No Known Activations