© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196162
    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_9_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
    ggplot
    0.48
     drawable
    0.46
     (#{
    0.46
     indexing
    0.45
     histological
    0.45
    <unused16>
    0.44
     accounted
    0.44
    HBO
    0.44
    摘要
    0.44
     tomar
    0.44
    POSITIVE LOGITS
     lời
    0.51
     most
    0.50
    ians
    0.50
    ows
    0.49
     candidats
    0.48
    C
    0.48
     ቅ
    0.48
     candidates
    0.47
     bourgeois
    0.46
     asparagus
    0.46
    Activations Density 0.000%

    No Known Activations