© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149615
    Prev
    Next
    INDEX
    Explanations

    salary expense

    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_23_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
    補
    0.30
    َّ
    0.30
    িয়ার
    0.30
    bottom
    0.29
    indle
    0.29
    basic
    0.29
    NOWLED
    0.29
    ftan
    0.29
    cumulative
    0.29
    ught
    0.28
    POSITIVE LOGITS
     montagnes
    0.32
     Sağ
    0.30
    墉
    0.29
    のだが
    0.29
     Hoh
    0.29
    эри
    0.28
     หนังสือ
    0.28
     मोड
    0.28
     mountains
    0.28
    荒
    0.28
    Activations Density 0.052%

    No Known Activations