© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132067
    Prev
    Next
    INDEX
    Explanations

    collection of items

    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
    ية
    1.45
    in
    1.30
    es
    1.30
    al
    1.20
    am
    1.15
    d
    1.12
    k
    1.11
    kta
    1.09
    śmy
    1.09
    ang
    1.05
    POSITIVE LOGITS
    。
    0.89
    $
    0.86
    лу
    0.85
    ，
    0.83
     prodig
    0.82
    ੋ
    0.81
    0.78
     musician
    0.77
     progression
    0.77
     flashlight
    0.77
    Activations Density 0.001%

    No Known Activations