© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107257
    Prev
    Next
    INDEX
    Explanations

    Wojciech Zaremba, Jarosz

    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_2_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
    ↵
    1.00
    ine
    0.99
    哽
    0.96
    ie
    0.93
    nych
    0.92
    ikale
    0.90
    as
    0.89
     وس
    0.88
    ́a
    0.88
    elist
    0.86
    POSITIVE LOGITS
     is
    1.73
    ۔
    1.55
    r
    1.48
    は
    1.48
    ב
    1.47
    д
    1.36
    1.35
    "
    1.30
    ди
    1.28
    г
    1.23
    Activations Density 0.000%

    No Known Activations