© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205606
    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_37_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
     receipt
    0.40
    Θ
    0.38
     laud
    0.37
     stata
    0.37
    сси
    0.37
    ペーン
    0.37
     encounters
    0.37
    куль
    0.37
     requested
    0.36
     shrink
    0.35
    POSITIVE LOGITS
    nasa
    0.39
     نعرف
    0.39
    ')[
    0.37
    flickr
    0.37
    teryx
    0.37
    innam
    0.36
     Pati
    0.36
    Nec
    0.35
     yeti
    0.35
     قتل
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.