© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35099
    Prev
    Next
    INDEX
    Explanations

    all, every, kol

    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_7_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
     is
    1.35
    2
    1.28
    是
    1.27
     to
    1.19
    1
    0.98
    .¹
    0.95
    mu
    0.91
    ères
    0.88
    ni
    0.87
     eivät
    0.86
    POSITIVE LOGITS
    T
    1.13
    W
    1.13
    H
    1.07
    X
    1.00
    N
    0.99
    M
    0.98
    B
    0.98
    P
    0.97
    R
    0.93
    V
    0.93
    Activations Density 0.000%

    No Known Activations