© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5157
    Prev
    Next
    INDEX
    Explanations

    industry sector + related role/topic

    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_39_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
     distinct
    0.42
     rø
    0.41
     H
    0.39
    0.39
     reflecting
    0.38
     view
    0.37
     rotated
    0.37
     Alk
    0.37
    ake
    0.37
    ven
    0.37
    POSITIVE LOGITS
     offshoring
    0.46
    კის
    0.45
    ленд
    0.45
    应急
    0.45
    㓶
    0.45
     आपात
    0.44
    ផលិត
    0.44
    কেশন
    0.43
     緊急
    0.43
    ጷ
    0.43
    Activations Density 0.130%

    No Known Activations