© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241293
    Prev
    Next
    INDEX
    Explanations

    meeting standards and requirements

    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_40_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
     selon
    0.42
     objection
    0.41
    좇
    0.41
     Publication
    0.40
     Тех
    0.38
     سافٹ
    0.38
     technician
    0.38
     Técnico
    0.38
     rectification
    0.38
     Informatics
    0.38
    POSITIVE LOGITS
    aita
    0.42
    亣
    0.41
    eserc
    0.39
     required
    0.38
     exercises
    0.38
     निर्धार
    0.37
    WindowConstants
    0.37
    presets
    0.36
    REQUIRED
    0.36
     segmented
    0.36
    Activations Density 0.004%

    No Known Activations