© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203732
    Prev
    Next
    INDEX
    Explanations

    open

    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_37_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
     O
    0.50
     ओपी
    0.38
    瓯
    0.38
     OL
    0.37
    <unused400>
    0.37
     ওসি
    0.36
     О
    0.36
    cedure
    0.36
    𝑂
    0.35
    вете
    0.35
    POSITIVE LOGITS
    )$
    0.37
     विद्यालय
    0.35
     stopp
    0.34
     substantial
    0.34
     $)
    0.32
    웃
    0.32
     Tera
    0.32
    antes
    0.32
    殼
    0.32
     ES
    0.31
    Activations Density 0.020%

    No Known Activations