© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89147
    Prev
    Next
    INDEX
    Explanations

    sending, uploading, writing

    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_23_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
    标签
    0.21
     nouns
    0.20
     سلاټ
    0.20
     则
    0.20
    步骤
    0.20
     자신
    0.20
    ಿಸಿಕೊಂಡ
    0.20
    则
    0.20
    rasında
    0.20
    
    0.20
    POSITIVE LOGITS
     dispersal
    0.22
    評
    0.21
     palette
    0.21
     purse
    0.21
    Monitoring
    0.21
     ಯೋಜನೆ
    0.21
    駑
    0.21
     அமைச்ச
    0.20
     अनुभ
    0.20
     Transport
    0.20
    Activations Density 0.006%

    No Known Activations