© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218562
    Prev
    Next
    INDEX
    Explanations

    function parts

    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_47_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
    adeloupe
    0.39
    桶
    0.39
    ಪೆ
    0.37
    အရ
    0.37
     गांठ
    0.37
    たつ
    0.37
    posure
    0.37
    STER
    0.36
    สึก
    0.36
    屬
    0.36
    POSITIVE LOGITS
    ias
    0.44
    IAS
    0.42
     IAS
    0.42
    iai
    0.40
    znál
    0.38
     mou
    0.38
    իտ
    0.38
    iae
    0.37
    annan
    0.37
    itatud
    0.37
    Activations Density 0.000%

    No Known Activations