© 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. 123963
    Prev
    Next
    INDEX
    Explanations

    brewery, Ocean, Institute, data, performance

    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
    ar
    0.89
    il
    0.79
    in
    0.76
    l
    0.74
    u
    0.71
    b
    0.68
    st
    0.66
    w
    0.66
    suc
    0.64
    is
    0.63
    POSITIVE LOGITS
    ’
    0.82
    B
    0.70
    TE
    0.64
     be
    0.64
    י
    0.63
    MI
    0.62
     ix
    0.61
    C
    0.57
    ாத
    0.57
    M
    0.57
    Activations Density 0.013%

    No Known Activations