© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260081
    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_22_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
    2
    0.49
     Ian
    0.49
     More
    0.42
     Barr
    0.41
     monarch
    0.41
     du
    0.41
     germ
    0.41
     that
    0.41
     eight
    0.41
     Viv
    0.40
    POSITIVE LOGITS
     Вікіпедії
    0.53
    Ϥ
    0.50
    <unused32>
    0.49
    ட்சய
    0.49
    unsaturated
    0.49
    IER
    0.48
    <unused307>
    0.48
    িশালী
    0.48
    𝘏
    0.48
     precipitated
    0.48
    Activations Density 0.000%

    No Known Activations