© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18413
    Prev
    Next
    INDEX
    Explanations

    arn or id

    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_34_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
    PlusEvents
    0.40
     রাষ্ট্রদূত
    0.36
     біль
    0.35
    
    0.35
    ামূলক
    0.34
    вера
    0.34
    
    0.34
    rá
    0.33
    APA
    0.33
     apo
    0.33
    POSITIVE LOGITS
     nace
    0.43
     Meal
    0.40
     nasce
    0.39
     surgir
    0.39
     With
    0.38
     Neo
    0.38
     surgi
    0.37
     neo
    0.37
     ఉంటుంది
    0.37
     Yee
    0.36
    Activations Density 0.003%

    No Known Activations