© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89445
    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_23_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
    箴
    0.64
    żs
    0.52
     भर
    0.50
    ieck
    0.49
    ę
    0.48
     ማለት
    0.48
     कार्यवाही
    0.47
    ämp
    0.47
     matériau
    0.47
    ents
    0.46
    POSITIVE LOGITS
     fathom
    0.54
     celebrities
    0.51
     indulge
    0.49
    丑
    0.48
     permit
    0.48
     ugly
    0.47
    Watched
    0.47
     rename
    0.47
     Ples
    0.47
     renunci
    0.46
    Activations Density 0.000%

    No Known Activations