© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2429
    Prev
    Next
    INDEX
    Explanations

    yes or no answers

    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_38_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
     PR
    0.43
    öny
    0.39
    pertensive
    0.38
    羮
    0.37
    PR
    0.36
     බැ
    0.35
    쩡
    0.35
     menjal
    0.34
    AddNew
    0.33
    obenz
    0.33
    POSITIVE LOGITS
     Absolutely
    0.54
     absolutely
    0.49
    Absolutely
    0.46
     no
    0.44
     No
    0.43
     ሚ
    0.40
     Sort
    0.39
    ock
    0.37
     разделить
    0.37
    absolutely
    0.37
    Activations Density 0.259%

    No Known Activations