© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 203980
    Prev
    Next
    INDEX
    Explanations

    franc

    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
    matcher
    0.38
     kissed
    0.38
    jaa
    0.37
    钤
    0.37
     kiss
    0.36
     kass
    0.36
     AGRICULTURAL
    0.36
    袖
    0.36
    SALT
    0.35
     salt
    0.35
    POSITIVE LOGITS
     frank
    1.08
    Frank
    1.06
     Franc
    0.98
     фран
    0.98
     Фран
    0.96
     Frank
    0.95
     francs
    0.93
    frank
    0.91
    Franc
    0.90
     franc
    0.89
    Activations Density 0.011%

    No Known Activations