© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52674
    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_55_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
     mekan
    0.43
     distinguir
    0.43
    কন
    0.40
    沘
    0.40
     distinguer
    0.39
     окна
    0.39
    Iterations
    0.39
     distingue
    0.38
     accessToken
    0.38
     Chirurg
    0.38
    POSITIVE LOGITS
    [
    0.42
     WC
    0.40
     d
    0.39
     see
    0.39
     generally
    0.39
     oh
    0.38
    .,
    0.38
     Google
    0.37
     twenty
    0.37
     ;
    0.37
    Activations Density 0.000%

    No Known Activations