© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104457
    Prev
    Next
    INDEX
    Explanations

    Yarra River, Yaris, YTM

    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
     a
    1.37
     be
    1.14
     jeopard
    1.13
     to
    1.07
    কে
    1.05
     have
    1.02
    0
    0.97
    ্স
    0.93
    inę
    0.93
     już
    0.92
    POSITIVE LOGITS
    t
    1.39
    r
    1.28
    ت
    1.25
    。
    1.18
    l
    1.09
    ان
    1.06
    ле
    1.04
    ار
    1.03
    oc
    1.02
    ac
    1.01
    Activations Density 0.000%

    No Known Activations