© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32903
    Prev
    Next
    INDEX
    Explanations

    deals with

    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_31_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
     бекер
    0.43
    逘
    0.42
     医学
    0.42
    ദ്യം
    0.40
    дору
    0.39
     Міні
    0.38
     theologians
    0.38
    啾
    0.37
     труда
    0.37
    Geometry
    0.37
    POSITIVE LOGITS
     supplies
    0.42
     with
    0.38
     dangerous
    0.38
     broadly
    0.38
     companies
    0.37
    ,"\
    0.37
     partially
    0.37
     converts
    0.36
     renders
    0.36
     corporations
    0.35
    Activations Density 0.005%

    No Known Activations