© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5666
    Prev
    Next
    INDEX
    Explanations

    simply recipes or online OCR

    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_39_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
     comprehensive
    0.42
     BuildConfig
    0.42
    ﹀
    0.41
     তর্ক
    0.41
    
    0.39
    ▽
    0.39
     experimento
    0.39
     টিকে
    0.38
    
    0.38
    ロジー
    0.38
    POSITIVE LOGITS
    apa
    0.50
     apa
    0.39
     Toh
    0.37
     Merc
    0.36
     din
    0.35
    bet
    0.35
    स्थित
    0.35
    ada
    0.35
    ato
    0.35
     Papa
    0.35
    Activations Density 0.001%

    No Known Activations