© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156614
    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_2_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
    i
    0.71
    ५
    0.60
    an
    0.59
    I
    0.59
    {
    0.57
    -
    0.55
    lichkeit
    0.54
    ৯
    0.54
    E
    0.53
    ۹
    0.53
    POSITIVE LOGITS
    س
    0.64
    ش
    0.57
    re
    0.51
    स
    0.51
    ने
    0.50
    سلم
    0.50
    ड
    0.50
     automaker
    0.49
     Bisby
    0.49
    ری
    0.48
    Activations Density 0.000%

    No Known Activations