© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32582
    Prev
    Next
    INDEX
    Explanations

    closing code blocks }

    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_31_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
     feet
    0.30
    unwrap
    0.29
     mooring
    0.29
     bottom
    0.28
     plaus
    0.27
    唑
    0.27
    again
    0.27
     nghiệp
    0.27
    分の
    0.27
     stare
    0.26
    POSITIVE LOGITS
    STOCK
    0.28
     ሂ
    0.28
    стане
    0.27
    лат
    0.27
    ilberger
    0.27
     spé
    0.26
     Seaton
    0.26
    縷
    0.26
     теркә
    0.26
    Luckily
    0.26
    Activations Density 0.001%

    No Known Activations