© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104297
    Prev
    Next
    INDEX
    Explanations

    Russian requests for generation

    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_1_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
    with
    1.53
    en
    1.41
    n
    1.38
    w
    1.38
     with
    1.37
    ut
    1.36
    on
    1.35
     be
    1.34
    to
    1.29
    u
    1.27
    POSITIVE LOGITS
    чи
    1.03
    ありますが
    0.91
    د
    0.90
    кме
    0.88
    大
    0.88
     опреде
    0.87
    مكن
    0.87
     إضافة
    0.87
    locationY
    0.87
    ンテ
    0.86
    Activations Density 0.001%

    No Known Activations