© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233025
    Prev
    Next
    INDEX
    Explanations

    SciPy optimization methods

    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
    ')[
    0.41
    เภ
    0.40
     Grill
    0.39
     explored
    0.38
    versa
    0.37
     looking
    0.37
     Phar
    0.36
    Mitchell
    0.36
    vants
    0.36
    宥
    0.36
    POSITIVE LOGITS
     dyst
    0.40
    
    0.40
     outcomes
    0.38
     실시
    0.38
     tốt
    0.38
     voix
    0.38
     Outcomes
    0.38
    तला
    0.38
     duration
    0.37
     声
    0.37
    Activations Density 0.000%

    No Known Activations