© 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. 98493
    Prev
    Next
    INDEX
    Explanations

    integer and integral operations

    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
    好きな
    0.58
    伝え
    0.54
     Александр
    0.53
    し
    0.53
    USB
    0.53
    洺
    0.52
    െയി
    0.52
    人の
    0.50
    Irish
    0.50
    اندان
    0.50
    POSITIVE LOGITS
    at
    0.49
    kne
    0.45
     â
    0.45
     de
    0.44
    ät
    0.44
     十
    0.44
     redo
    0.43
    <0xBF>
    0.42
     met
    0.42
    raft
    0.42
    Activations Density 0.000%

    No Known Activations