© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179340
    Prev
    Next
    INDEX
    Explanations

    bound

    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_50_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
     yılları
    0.39
    abay
    0.37
    燃料
    0.35
     നിങ്ങൾ
    0.35
     ধরন
    0.34
    𝐋
    0.34
     bangunan
    0.34
    Przy
    0.33
    -¹
    0.33
    чему
    0.33
    POSITIVE LOGITS
    ed
    0.49
     redact
    0.41
    reo
    0.39
    ieft
    0.39
    edu
    0.38
    let
    0.38
    utica
    0.38
    Jets
    0.38
     Eo
    0.38
    ΟΣ
    0.37
    Activations Density 0.002%

    No Known Activations