© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132704
    Prev
    Next
    INDEX
    Explanations

    curly braces and sequences

    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
    se
    1.22
     \
    1.17
    ons
    1.16
    oh
    1.13
    app
    1.09
    r
    1.09
    ↵
    1.08
    s
    1.08
    ر
    1.06
    রা
    1.05
    POSITIVE LOGITS
    <bos>
    1.39
    ۳
    1.13
    ،
    1.11
     نیز
    1.10
    nW
    1.04
     غير
    1.03
     کنم
    1.03
    izowane
    1.02
    かけた
    1.02
    ༨
    1.02
    Activations Density 0.000%

    No Known Activations