© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15413
    Prev
    Next
    INDEX
    Explanations

    scripture verse numbers

    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_40_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
     वाया
    0.08
     Simultaneously
    0.08
     बाली
    0.07
     dehyd
    0.07
     ব্যাপারটা
    0.07
    <unused3>
    0.07
    ávají
    0.07
     faker
    0.07
    蜒
    0.07
    轺
    0.07
    POSITIVE LOGITS
     seventeen
    0.10
     fifteen
    0.10
     forty
    0.09
     twelfth
    0.09
     eleventh
    0.09
     fourteen
    0.09
     eighteen
    0.09
     twenty
    0.09
     twelve
    0.09
     £
    0.08
    Activations Density 0.028%

    No Known Activations