© 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. 155918
    Prev
    Next
    INDEX
    Explanations

    Florence

    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
     Pneum
    0.48
    Peter
    0.45
     PETER
    0.43
     pneum
    0.42
     pneumatic
    0.42
    桐
    0.42
    peter
    0.40
     بول
    0.40
    躹
    0.40
     Peter
    0.39
    POSITIVE LOGITS
     flore
    1.07
     Florence
    0.96
    Florence
    0.96
     Фло
    0.96
     Florent
    0.95
     Flore
    0.93
     Floren
    0.85
    Flore
    0.80
     Firenze
    0.79
     Fiorent
    0.78
    Activations Density 0.000%

    No Known Activations