© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118518
    Prev
    Next
    INDEX
    Explanations

    parameters, system components, configurations

    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_27_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
     comparable
    0.30
     należy
    0.29
     salient
    0.29
    ạm
    0.29
    忘
    0.28
    şı
    0.28
    itiert
    0.28
    ₄
    0.28
     grabación
    0.28
     impres
    0.28
    POSITIVE LOGITS
     थाने
    0.33
    刦
    0.33
    帑
    0.31
     soms
    0.31
     डेंगू
    0.31
    ామ
    0.30
    薀
    0.29
    ccgi
    0.29
     кілька
    0.29
    
    0.29
    Activations Density 0.000%

    No Known Activations