© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174702
    Prev
    Next
    INDEX
    Explanations

    ethical considerations

    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
     sejam
    0.30
    报警
    0.26
     malfunctioning
    0.26
     confounding
    0.26
    违法
    0.25
     drunkenness
    0.25
    ଵ
    0.25
     sebagaimana
    0.25
     malfunctions
    0.25
    abu
    0.25
    POSITIVE LOGITS
    vehicle
    0.28
    Bits
    0.28
    who
    0.28
     vü
    0.27
    匠
    0.26
    Entire
    0.25
    Bitt
    0.25
     allows
    0.25
    Orient
    0.25
     আত্মীয়
    0.24
    Activations Density 0.031%

    No Known Activations