© 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. 51158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    o
    0.62
    is
    0.61
    p
    0.60
    in
    0.58
    are
    0.51
    to
    0.51
    z
    0.51
    j
    0.48
    u
    0.48
    for
    0.47
    POSITIVE LOGITS
    Чтобы
    0.46
    Translatef
    0.45
    }_{[
    0.44
     podríamos
    0.44
     podrían
    0.43
    👛
    0.43
    ₮
    0.43
    Proble
    0.43
    ټبال
    0.42
    ™,
    0.42
    Activations Density 0.000%

    No Known Activations