© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26632
    Prev
    Next
    INDEX
    Explanations

    make file

    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_10_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
     made
    0.70
     MADE
    0.68
     و
    0.64
     gemacht
    0.64
     gemaakt
    0.62
     maken
    0.60
     Made
    0.59
     व
    0.58
    {
    0.58
    0.58
    POSITIVE LOGITS
    0
    0.71
    ะ
    0.71
    ש
    0.68
    א
    0.67
    odată
    0.64
    า
    0.64
     طاقت
    0.64
     przyję
    0.64
     потер
    0.63
     incest
    0.63
    Activations Density 0.045%

    No Known Activations