© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12451
    Prev
    Next
    INDEX
    Explanations

    Google Cloud and related services

    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
     thatched
    0.61
     peau
    0.59
     Pero
    0.57
     Teile
    0.56
     crushing
    0.55
     Teil
    0.55
     Ε
    0.55
     Архиви
    0.55
     आहे
    0.54
     Wordpress
    0.54
    POSITIVE LOGITS
    quantile
    0.51
    Minimize
    0.50
    Adjustment
    0.49
    곱
    0.49
    RMSE
    0.48
    Passenger
    0.47
    vert
    0.47
    Vertices
    0.47
    Reward
    0.47
    vertices
    0.46
    Activations Density 0.032%

    No Known Activations