© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34740
    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_7_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
     Fähigkeiten
    0.49
     Pressed
    0.47
     Frage
    0.47
    椑
    0.47
     Entfer
    0.47
    れます
    0.46
     Checked
    0.46
     Yatha
    0.46
     Quadrupèdes
    0.46
     ખો
    0.46
    POSITIVE LOGITS
     defense
    0.56
    :
    0.56
    adapt
    0.51
    ;
    0.49
     sanguine
    0.48
     favorable
    0.48
     hybrid
    0.48
     dollar
    0.48
     hybridization
    0.47
     partnerships
    0.47
    Activations Density 0.000%

    No Known Activations