© 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. 147473
    Prev
    Next
    INDEX
    Explanations

    GN

    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
    S
    0.57
    R
    0.52
    B
    0.50
    H
    0.47
    Ton
    0.40
    Ram
    0.40
    Lam
    0.39
    Tam
    0.38
    Tl
    0.38
    Therm
    0.38
    POSITIVE LOGITS
    u
    0.55
    НО
    0.46
    inine
    0.44
    𝑁
    0.44
    eme
    0.43
    ANE
    0.43
    𝙉
    0.42
    ॉग
    0.41
    uppe
    0.41
    uhe
    0.41
    Activations Density 0.000%

    No Known Activations