© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59356
    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_59_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
     S
    0.50
     Σ
    0.46
    ┐
    0.43
    ewater
    0.43
     הס
    0.42
    tero
    0.41
    ymi
    0.41
    oretical
    0.40
    home
    0.40
    her
    0.39
    POSITIVE LOGITS
    CROSS
    0.43
    Cross
    0.42
    跨
    0.40
    си
    0.40
     CROSS
    0.39
    وف
    0.38
    .—
    0.38
    .“
    0.38
    .•
    0.38
     crosses
    0.37
    Activations Density 0.000%

    No Known Activations