© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81276
    Prev
    Next
    INDEX
    Explanations

    showed or shown

    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_31_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
    感
    0.39
     感
    0.39
     листопада
    0.37
     expertise
    0.37
     senc
    0.37
     perspectiva
    0.36
     конструкция
    0.36
     semble
    0.35
     温度
    0.35
    道理
    0.35
    POSITIVE LOGITS
    ikke
    0.43
    ınd
    0.42
    erty
    0.41
     Resistant
    0.40
    roda
    0.39
     Vel
    0.38
    ༸
    0.38
    の変化
    0.38
    abis
    0.38
    Mid
    0.36
    Activations Density 0.002%

    No Known Activations