© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142422
    Prev
    Next
    INDEX
    Explanations

    Odoo, book, attachment, module definitions

    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_12_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
     delimiters
    0.58
     ді
    0.56
     of
    0.51
     النبات
    0.50
     দ
    0.49
    স
    0.49
     ဒ
    0.48
    cón
    0.47
     ד
    0.47
     ecosystem
    0.46
    POSITIVE LOGITS
     administratif
    0.62
    VM
    0.61
    Shadow
    0.56
    etc
    0.55
     Publish
    0.55
    Recorder
    0.54
    NM
    0.54
     godina
    0.54
    publik
    0.54
     ANON
    0.54
    Activations Density 0.006%

    No Known Activations