© 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
    2. Gemma-3-27B-IT
    3. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 83669
    Prev
    Next
    INDEX
    Explanations

    macroeconomic topics and trends

    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_0_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
     краёва
    1.33
     Дмитрий
    1.32
    );//
    1.31
     Klan
    1.30
    PlayerDataCache
    1.30
    在
    1.29
     Само
    1.24
     Олег
    1.23
     Yaj
    1.23
     Игорь
    1.22
    POSITIVE LOGITS
    .
    2.14
    the
    2.03
    de
    1.65
    ali
    1.64
    t
    1.64
    í
    1.64
    an
    1.59
    ä
    1.56
    ing
    1.55
    v
    1.55
    Activations Density 0.000%

    No Known Activations