© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235692
    Prev
    Next
    INDEX
    Explanations

    items and equity

    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_46_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
    攣
    0.45
    ໂດຍ
    0.43
     بات
    0.42
    twilio
    0.40
    ადგენ
    0.39
    尿
    0.38
     integ
    0.37
     ব্যায়াম
    0.37
     direta
    0.37
    納
    0.37
    POSITIVE LOGITS
     Steep
    0.41
     equivalence
    0.41
     inequities
    0.40
     Equitable
    0.39
     item
    0.39
    item
    0.39
     inequ
    0.39
     Items
    0.38
     Item
    0.38
     Equ
    0.38
    Activations Density 0.003%

    No Known Activations