© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115242
    Prev
    Next
    INDEX
    Explanations

    more information

    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_27_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
     Football
    0.40
     DT
    0.37
     Im
    0.37
     rapid
    0.36
     fast
    0.34
     Spark
    0.33
     income
    0.33
     football
    0.33
     지
    0.33
     spark
    0.33
    POSITIVE LOGITS
    வார்கள்
    0.43
    िकांत
    0.38
    찍
    0.38
    CreateIndex
    0.37
     JUAN
    0.37
     էր
    0.35
     बनकर
    0.34
     REACTIONS
    0.34
    REACT
    0.34
    TYPES
    0.34
    Activations Density 0.005%

    No Known Activations