© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50147
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

    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_30_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
     dredge
    0.42
    idcar
    0.38
    atot
    0.38
    亠
    0.37
    än
    0.36
     kän
    0.36
     mixts
    0.36
    NetStandard
    0.36
    ⵡ
    0.36
     levou
    0.35
    POSITIVE LOGITS
    db
    0.38
     region
    0.37
     ერთი
    0.37
    setup
    0.37
    fx
    0.36
    flash
    0.36
    region
    0.34
     Sar
    0.34
     Collect
    0.34
    Setup
    0.34
    Activations Density 0.003%

    No Known Activations