© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47231
    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_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
     waterproofing
    0.50
    ڄ
    0.42
     Waterproof
    0.41
    d
    0.41
     rounds
    0.41
     waterproof
    0.40
    t
    0.40
     одна
    0.38
    Specification
    0.38
     subclasses
    0.38
    POSITIVE LOGITS
     हैं
    0.59
    umping
    0.55
     caja
    0.55
    ancang
    0.55
    uck
    0.55
    ers
    0.54
     Reino
    0.54
     nowego
    0.54
    ḩ
    0.54
     siente
    0.53
    Activations Density 0.000%

    No Known Activations