© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38936
    Prev
    Next
    INDEX
    Explanations

    attention to detail

    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_11_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
    0.83
    D
    0.78
    s
    0.77
    0
    0.70
    H
    0.68
    m
    0.66
    P
    0.65
    1
    0.64
    G
    0.62
    to
    0.61
    POSITIVE LOGITS
    ла
    0.61
     duplication
    0.57
     multitude
    0.55
    ochromatic
    0.55
     Zugang
    0.54
     программу
    0.52
    рим
    0.52
     chromatographed
    0.52
     diagonalization
    0.51
    ोग
    0.50
    Activations Density 0.010%

    No Known Activations