© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8579
    Prev
    Next
    INDEX
    Explanations

    explanation of code

    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
    Negative Logits
    。」
    0.16
    مود
    0.16
    、
    0.15
    zhou
    0.15
    uity
    0.15
     impairments
    0.15
     abstractions
    0.15
    Folders
    0.14
    ᠠ
    0.14
    mor
    0.14
    POSITIVE LOGITS
     Geheim
    0.16
     el
    0.15
     estudi
    0.15
     EXPL
    0.15
     служит
    0.14
    inairement
    0.14
     dos
    0.14
     нем
    0.14
    टे
    0.14
     altro
    0.14
    Activations Density 0.257%

    No Known Activations