© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102536
    Prev
    Next
    INDEX
    Explanations

    say Chinese characters

    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_44_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
    궐
    0.37
     зве
    0.36
    rogens
    0.35
     Precip
    0.34
    
    0.33
     Securities
    0.33
    Subgraph
    0.33
     생각이
    0.33
    שרה
    0.33
     مربوط
    0.32
    POSITIVE LOGITS
     mark
    0.38
     undocumented
    0.37
    ,|\
    0.36
    𠄌
    0.36
     okay
    0.35
     purging
    0.34
     engines
    0.34
     securely
    0.34
     waived
    0.34
     quantization
    0.34
    Activations Density 0.000%

    No Known Activations