© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84977
    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_23_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
     fringe
    0.40
    Coverage
    0.40
    DEA
    0.40
     timbre
    0.40
    <
    0.39
    Allocation
    0.39
     placement
    0.37
    Location
    0.36
     Cover
    0.36
     bushel
    0.36
    POSITIVE LOGITS
    श्री
    0.46
    厓
    0.43
     时尚
    0.43
     શ્રી
    0.43
     ट्रेन
    0.42
     सलीम
    0.42
     Sven
    0.41
    São
    0.40
    സ്റ്റി
    0.40
    妮
    0.40
    Activations Density 0.000%

    No Known Activations