© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106569
    Prev
    Next
    INDEX
    Explanations

    step followed by numbers or structure

    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_1_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
    ت
    1.63
    고
    1.62
    т
    1.46
    是
    1.42
    تان
    1.34
    те
    1.30
     are
    1.16
    ↵↵
    1.15
    تين
    1.15
    る
    1.15
    POSITIVE LOGITS
    st
    1.14
     σε
    1.14
    ian
    1.13
    い
    1.03
    c
    0.99
    ต์
    0.99
    deki
    0.93
     in
    0.92
     في
    0.88
    ,
    0.88
    Activations Density 0.001%

    No Known Activations