© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206217
    Prev
    Next
    INDEX
    Explanations

    date October

    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_25_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
     anatomical
    0.41
     appearance
    0.38
    Driver
    0.38
    USES
    0.38
     maturity
    0.37
    Patent
    0.37
    二
    0.37
    术
    0.37
     surfing
    0.37
     ഇരു
    0.36
    POSITIVE LOGITS
     eğer
    0.47
     bela
    0.44
     daca
    0.40
     dacă
    0.38
     Premi
    0.38
     budou
    0.38
     Threatened
    0.37
     principais
    0.37
     Bela
    0.36
     Ends
    0.36
    Activations Density 0.006%

    No Known Activations