© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68778
    Prev
    Next
    INDEX
    Explanations

    clean

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    катери
    0.37
    драв
    0.36
    AuditEvent
    0.35
     squid
    0.34
     Squid
    0.34
    iotsitewise
    0.34
     แก้
    0.34
    
    0.34
     பிரி
    0.34
    ಷ್ಣ
    0.34
    POSITIVE LOGITS
     clean
    3.30
    clean
    3.08
     Clean
    3.06
    Clean
    3.05
     CLEAN
    2.77
     cleanliness
    2.53
    清洁
    2.53
     temiz
    2.53
     cleaner
    2.44
     cleanest
    2.44
    Activations Density 0.003%

    No Known Activations