© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45687
    Prev
    Next
    INDEX
    Explanations

    qDebug() or Radar logs

    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_3_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
    an
    1.18
    a
    1.10
    as
    1.02
    at
    0.91
    i
    0.89
    r
    0.89
    es
    0.87
    ar
    0.87
    re
    0.84
    ab
    0.82
    POSITIVE LOGITS
    ность
    0.64
     constituent
    0.64
    marshalN
    0.61
    を使用
    0.60
     subparagraph
    0.60
     predator
    0.59
     반
    0.58
     tertentu
    0.57
     Тео
    0.57
    ))
    0.56
    Activations Density 0.003%

    No Known Activations