© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13912
    Prev
    Next
    INDEX
    Explanations

    principal component analysis

    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_13_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
     как
    0.51
     ANN
    0.49
     AR
    0.48
     amantes
    0.47
     BRANCH
    0.46
     ос
    0.46
     [&](
    0.46
     Hadoop
    0.46
     ou
    0.45
    ђе
    0.45
    POSITIVE LOGITS
    g
    0.50
    stone
    0.48
    co
    0.48
    "
    0.47
    up
    0.46
    free
    0.45
    gs
    0.45
    C
    0.45
    fire
    0.44
    Cap
    0.44
    Activations Density 0.005%

    No Known Activations