© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154337
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    t
    0.68
    take
    0.68
    to
    0.67
    ti
    0.62
    set
    0.61
    time
    0.61
    day
    0.59
    na
    0.58
    string
    0.58
    tak
    0.55
    POSITIVE LOGITS
     Dish
    0.50
     Drone
    0.47
     Den
    0.46
     Deg
    0.45
    ĭ
    0.45
     Dey
    0.45
     ڈ
    0.44
     parametros
    0.44
     Descriptor
    0.43
     descripcion
    0.43
    Activations Density 0.000%

    No Known Activations