© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61374
    Prev
    Next
    INDEX
    Explanations

    curly braces

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    さに
    0.43
     is
    0.43
     (
    0.42
    (
    0.39
    は
    0.39
     agus
    0.38
    又は
    0.38
    tev
    0.38
     denaturation
    0.38
     hoặc
    0.38
    POSITIVE LOGITS
    <h4>
    0.42
    करी
    0.38
    <h3>
    0.38
    `<
    0.37
    ква
    0.35
    Fab
    0.35
    console
    0.35
    ]<
    0.34
    ൽ
    0.33
    ',()=>{
    0.33
    Activations Density 0.001%

    No Known Activations