© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234650
    Prev
    Next
    INDEX
    Explanations

    backwards, loss, electrons, snapshots

    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_32_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
    停留
    0.73
    stopped
    0.69
    停
    0.68
     stopped
    0.66
     stagn
    0.66
     останови
    0.66
     stagnant
    0.64
     останов
    0.64
    stop
    0.63
    멈
    0.63
    POSITIVE LOGITS
     Herr
    0.39
     Habit
    0.38
     father
    0.37
     গড়ে
    0.37
     açúcar
    0.37
     rowIndex
    0.37
     sharpen
    0.36
     philosoph
    0.36
    inerja
    0.36
     invent
    0.35
    Activations Density 0.038%

    No Known Activations