© 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. 16036
    Prev
    Next
    INDEX
    Explanations

    provide the text

    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
    atus
    0.39
     مقدم
    0.37
     menget
    0.36
    èo
    0.35
     propulsion
    0.35
    oje
    0.35
     rep
    0.34
    jon
    0.34
    ঙ্ঘ
    0.34
    +#+#+
    0.34
    POSITIVE LOGITS
    降
    0.36
    ModelAdmin
    0.36
    補
    0.36
    Def
    0.35
     चाहर
    0.35
     Superhero
    0.35
    Super
    0.35
     Bond
    0.35
     bonds
    0.34
     llrp
    0.34
    Activations Density 0.045%

    No Known Activations