© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82980
    Prev
    Next
    INDEX
    Explanations

    finite states, volume, products, methods

    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
     as
    1.80
    ва
    1.32
    एस
    1.23
    리
    1.22
    ер
    1.20
    ため
    1.16
    ر
    1.15
    رین
    1.13
     histological
    1.09
    لین
    1.09
    POSITIVE LOGITS
    ，
    1.34
    ka
    1.30
    ↵↵
    1.23
    ak
    1.23
    p
    1.18
    ،
    1.18
    ia
    1.16
    ang
    1.16
    ma
    1.15
    ا
    1.12
    Activations Density 0.000%

    No Known Activations