© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133201
    Prev
    Next
    INDEX
    Explanations

    roman numerals

    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_1_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
    B
    1.81
    D
    1.77
    G
    1.63
    H
    1.53
    W
    1.51
    J
    1.42
    K
    1.40
    U
    1.38
    V
    1.34
    C
    1.33
    POSITIVE LOGITS
    s
    1.30
    a
    1.27
    س
    1.23
    o
    1.23
    y
    1.16
    i
    1.14
     a
    1.13
    lor
    1.09
    ्स
    1.07
    ds
    1.07
    Activations Density 0.000%

    No Known Activations