© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228619
    Prev
    Next
    INDEX
    Explanations

    Ferris wheel, Clear, Covey

    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_6_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
    তত্ব
    0.96
     Btu
    0.85
    𝚋
    0.85
    يال
    0.84
    <0x80>
    0.82
    Ⲕ
    0.82
     OFF
    0.80
    𝐿
    0.80
    ၻ
    0.80
    𝐵
    0.80
    POSITIVE LOGITS
    in
    1.39
    re
    1.13
    is
    1.05
    un
    1.02
    os
    1.00
    ot
    0.97
    1
    0.97
    im
    0.95
    é
    0.93
    s
    0.90
    Activations Density 0.001%

    No Known Activations