© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88177
    Prev
    Next
    INDEX
    Explanations

    async Task Main

    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_3_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
    ।
    0.87
    can
    0.72
    f
    0.71
    stato
    0.70
    ls
    0.69
    cs
    0.66
    Enabled
    0.64
     Франция
    0.64
    be
    0.63
    culos
    0.63
    POSITIVE LOGITS
     mají
    0.73
     имат
    0.65
     jeopard
    0.64
     е
    0.63
    ことなく
    0.61
    ো
    0.61
     tổng
    0.60
     dolayı
    0.59
     categor
    0.59
     hanno
    0.59
    Activations Density 0.001%

    No Known Activations