© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148372
    Prev
    Next
    INDEX
    Explanations

    column names and descriptions

    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_23_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
     horseshoe
    0.41
     lighthouse
    0.38
     acacia
    0.35
    皈
    0.35
     kiddos
    0.35
     substitutes
    0.34
     LPA
    0.34
     almond
    0.34
     plush
    0.34
     sculptures
    0.34
    POSITIVE LOGITS
    GLISH
    0.36
     સત
    0.36
    নিত
    0.35
     Volunte
    0.34
     प्रकट
    0.33
     който
    0.33
     అలాంటి
    0.33
    темати
    0.33
    㝡
    0.32
    }',
    0.32
    Activations Density 0.011%

    No Known Activations