© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35686
    Prev
    Next
    INDEX
    Explanations

    Galaxy

    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_50_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
    葭
    0.47
     tension
    0.38
     qs
    0.37
    家具
    0.36
     Kle
    0.36
     Ambos
    0.36
    __()
    0.36
     RARRAY
    0.35
     J
    0.35
    紧张
    0.35
    POSITIVE LOGITS
     bully
    0.42
     gal
    0.42
     GAL
    0.42
    italic
    0.40
    পে
    0.40
    Galaxy
    0.39
     desapar
    0.38
    Gal
    0.38
     Gal
    0.38
    ssc
    0.38
    Activations Density 0.002%

    No Known Activations