© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198079
    Prev
    Next
    INDEX
    Explanations

    fungible tokens

    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_4_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
    .
    1.10
    at
    0.96
    م
    0.82
    。
    0.81
    .。
    0.77
    ม
    0.77
    飞
    0.68
    OM
    0.67
    UT
    0.66
    9
    0.65
    POSITIVE LOGITS
     विक्रे
    0.75
     বণ
    0.70
     પારિજા
    0.70
    sType
    0.69
     дизай
    0.68
     Система
    0.68
    t
    0.68
    edLeft
    0.67
     издания
    0.67
    𒆪
    0.66
    Activations Density 0.000%

    No Known Activations