© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242175
    Prev
    Next
    INDEX
    Explanations

    extra credit assignments

    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_25_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
    あなたは
    0.42
    ंपूर्
    0.40
    гна
    0.40
    withTrashed
    0.40
     والث
    0.40
    ាហ
    0.39
     katol
    0.39
    કારી
    0.38
    ଭ
    0.38
    ᴠ
    0.38
    POSITIVE LOGITS
     Journey
    0.44
     Calculation
    0.40
     Journal
    0.40
     Art
    0.40
     Us
    0.39
     Oxygen
    0.39
     Aesthetic
    0.39
     Phot
    0.39
     Document
    0.38
    Phys
    0.38
    Activations Density 0.000%

    No Known Activations