© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195169
    Prev
    Next
    INDEX
    Explanations

    name Kai, Moonbeam, or Main Control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     باہر
    0.55
    families
    0.55
     insuffisamment
    0.53
    ᱕
    0.52
     prédio
    0.52
    رسٹ
    0.52
     ाट
    0.50
    ults
    0.50
    operations
    0.49
     .{
    0.49
    POSITIVE LOGITS
     (
    0.58
     d
    0.55
     la
    0.54
     Chai
    0.54
     ph
    0.54
     chai
    0.53
     garden
    0.52
     Ter
    0.51
     solar
    0.50
    (
    0.50
    Activations Density 0.000%

    No Known Activations