© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218132
    Prev
    Next
    INDEX
    Explanations

    math problem

    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_16_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
    빈
    0.51
    si
    0.46
     is
    0.45
    д
    0.44
     фран
    0.44
     державних
    0.44
     Бер
    0.43
    counting
    0.43
    יי
    0.43
     booming
    0.42
    POSITIVE LOGITS
     stets
    0.51
    prite
    0.47
     selalu
    0.46
    N
    0.46
    RUP
    0.45
    ak
    0.44
    口气
    0.44
    emeni
    0.43
    emal
    0.43
    pped
    0.42
    Activations Density 0.000%

    No Known Activations