© 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. 221752
    Prev
    Next
    INDEX
    Explanations

    should have

    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
    N
    0.64
    Y
    0.61
    Q
    0.61
    U
    0.60
    W
    0.57
     to
    0.55
    R
    0.55
    H
    0.55
    T
    0.54
    y
    0.52
    POSITIVE LOGITS
    ουσ
    0.32
    сэн
    0.31
    ód
    0.29
    ност
    0.28
     raisons
    0.28
     molécules
    0.28
    atories
    0.28
     anciens
    0.28
    és
    0.27
    섣
    0.27
    Activations Density 0.016%

    No Known Activations