© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27063
    Prev
    Next
    INDEX
    Explanations

    python.org/downloads/windows/

    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_40_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
     つい
    0.36
    🩶
    0.35
    
    0.35
     setActive
    0.34
     лаь
    0.33
    ྐ
    0.33
     biens
    0.33
     biennial
    0.33
    
    0.32
    مال
    0.32
    POSITIVE LOGITS
     Me
    0.38
    Me
    0.36
    Classic
    0.36
    eyen
    0.35
    स्थान
    0.35
     self
    0.34
     tableName
    0.33
    Gor
    0.33
    Burst
    0.33
    orf
    0.32
    Activations Density 0.000%

    No Known Activations