© 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. 174381
    Prev
    Next
    INDEX
    Explanations

    that the

    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
    an
    0.29
    anas
    0.27
    anj
    0.26
    ood
    0.26
    ki
    0.25
     появится
    0.25
    士
    0.25
    expenses
    0.24
    ਜ਼
    0.24
    irting
    0.24
    POSITIVE LOGITS
     -=
    0.31
     proportion
    0.28
     quantify
    0.27
     tỷ
    0.27
     kē
    0.27
     proportionally
    0.27
     proportionately
    0.26
     dl
    0.26
     двой
    0.26
     dekh
    0.26
    Activations Density 0.003%

    No Known Activations