© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81161
    Prev
    Next
    INDEX
    Explanations

    port related contexts

    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_0_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
    sw
    1.17
     (
    1.13
    sm
    1.04
    たん
    1.03
    am
    0.99
    ang
    0.98
    نی
    0.96
    ాలు
    0.96
     enseign
    0.96
    tenance
    0.94
    POSITIVE LOGITS
    ي
    2.34
    ה
    1.99
    a
    1.95
    ه
    1.88
    ۔
    1.82
    י
    1.78
    는
    1.77
    ა
    1.71
    ção
    1.68
    া
    1.66
    Activations Density 0.001%

    No Known Activations