© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216757
    Prev
    Next
    INDEX
    Explanations

    thorough

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    刄
    0.43
    hdad
    0.41
    णाली
    0.39
     diş
    0.39
    getChild
    0.39
    pyplot
    0.38
    Door
    0.38
     Bož
    0.38
    Servlet
    0.38
     BL
    0.38
    POSITIVE LOGITS
     f
    0.42
    使える
    0.39
    F
    0.39
     F
    0.38
     thorough
    0.35
     thoroughly
    0.35
    etar
    0.35
     ১৯৮
    0.35
     En
    0.35
     Thorough
    0.35
    Activations Density 0.000%

    No Known Activations