© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196103
    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_46_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
     sites
    0.42
     duch
    0.41
     datang
    0.38
    ficha
    0.38
     poche
    0.36
     Pseud
    0.36
    superclass
    0.35
    锲
    0.35
    Publication
    0.35
     každý
    0.35
    POSITIVE LOGITS
     simultaneously
    0.48
     concurrently
    0.43
     Simultaneously
    0.42
    同时
    0.42
    同時に
    0.39
     simultaneous
    0.39
    стки
    0.39
     동시에
    0.39
     samtidigt
    0.39
     samtidig
    0.38
    Activations Density 0.000%

    No Known Activations