© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209173
    Prev
    Next
    INDEX
    Explanations

    rights to or rights revert

    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_20_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
     Y
    0.29
     ν
    0.29
     Wes
    0.28
     Nu
    0.27
     Nieu
    0.27
     Greater
    0.27
    wijl
    0.26
     Elaine
    0.26
    เจ้า
    0.25
     Ka
    0.25
    POSITIVE LOGITS
    ⸙
    0.29
    atrix
    0.26
    Sequ
    0.26
    短期
    0.26
     врача
    0.26
     sanctions
    0.25
     multivalued
    0.25
     ရက်
    0.25
     proporcionar
    0.25
     sanciones
    0.25
    Activations Density 0.001%

    No Known Activations