© 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. 89019
    Prev
    Next
    INDEX
    Explanations

    asking for JSON output

    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_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
     Un
    0.39
     advent
    0.39
     නො
    0.38
     ntawm
    0.37
     ṣ
    0.36
     tejto
    0.36
     ({
    0.35
     throttling
    0.35
     btn
    0.34
     this
    0.34
    POSITIVE LOGITS
    kjav
    0.37
    謄
    0.35
     trộn
    0.34
     κά
    0.34
    lek
    0.34
    πων
    0.33
     прив
    0.33
    Джек
    0.33
    alek
    0.33
    lep
    0.33
    Activations Density 0.031%

    No Known Activations