© 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. 82238
    Prev
    Next
    INDEX
    Explanations

    broadcast scripts and games

    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
    д
    1.62
    тэй
    1.47
    تي
    1.42
    たん
    1.41
    るので
    1.35
    は
    1.34
    т
    1.33
    た
    1.32
    нибудь
    1.29
    نی
    1.27
    POSITIVE LOGITS
    ur
    1.79
    ab
    1.73
    1.71
    ang
    1.59
    ell
    1.53
    as
    1.52
    ar
    1.52
    ul
    1.44
    ou
    1.43
    ia
    1.40
    Activations Density 0.001%

    No Known Activations