© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46659
    Prev
    Next
    INDEX
    Explanations

    constructor or Construct

    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_13_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
    written
    0.54
    takes
    0.52
     लिखी
    0.49
    წერა
    0.49
    educated
    0.49
     televised
    0.48
    aniya
    0.47
     \
    0.47
    ער
    0.46
     apologizing
    0.46
    POSITIVE LOGITS
     combustível
    0.59
     irmã
    0.58
     বোন
    0.48
    ሁን
    0.47
     বট
    0.46
    Marin
    0.46
    噰
    0.46
     komplet
    0.45
     kod
    0.45
     рим
    0.45
    Activations Density 0.006%

    No Known Activations