© 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. 29856
    Prev
    Next
    INDEX
    Explanations

    quotes and code separators

    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
     activate
    0.38
    ufth
    0.36
     DIFFIC
    0.36
    ড়ি
    0.36
     arterios
    0.36
     Le
    0.36
     penal
    0.36
     beds
    0.35
    𝗘
    0.35
     trazendo
    0.35
    POSITIVE LOGITS
    Quotes
    0.38
     Quotes
    0.38
    Semi
    0.36
     полу
    0.35
    مول
    0.35
    Texts
    0.35
     Power
    0.35
     puol
    0.35
    <unused975>
    0.35
    TPP
    0.34
    Activations Density 0.001%

    No Known Activations