© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30079
    Prev
    Next
    INDEX
    Explanations

    Marjane Satrapi

    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_10_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
    f
    0.80
     it
    0.78
     he
    0.76
    ic
    0.68
    ite
    0.65
    ene
    0.64
     o
    0.63
    uk
    0.62
    out
    0.61
    ys
    0.59
    POSITIVE LOGITS
    ນາ
    0.66
    서는
    0.64
    արկ
    0.63
    ेश्वर
    0.61
    자
    0.58
    념
    0.58
    честве
    0.57
     bibliographic
    0.57
    م
    0.56
    在
    0.56
    Activations Density 0.005%

    No Known Activations