© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207070
    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_19_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
     has
    0.55
     knowledgeable
    0.48
    </h2>
    0.47
    Xa
    0.47
     sie
    0.45
    る
    0.45
    my
    0.44
     member
    0.43
     suggests
    0.43
     jockey
    0.43
    POSITIVE LOGITS
    د
    0.63
    स
    0.53
    ду
    0.50
    денти
    0.49
    श
    0.49
    ช
    0.47
    ชา
    0.45
    اس
    0.44
     Residual
    0.44
     Routine
    0.44
    Activations Density 0.000%

    No Known Activations