© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13638
    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_40_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
     உட்ப
    0.45
    呑
    0.43
     Terr
    0.43
    Terr
    0.40
    essi
    0.40
     Hlav
    0.40
     Milk
    0.39
     Request
    0.38
    onces
    0.38
     half
    0.37
    POSITIVE LOGITS
    Curtis
    0.43
    Jorge
    0.42
    ᱒
    0.41
    Louise
    0.40
     slider
    0.40
     فرن
    0.40
     rotor
    0.40
     ہوئے
    0.38
     sorpre
    0.38
     Jacobsen
    0.38
    Activations Density 0.000%

    No Known Activations