© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87474
    Prev
    Next
    INDEX
    Explanations

    Taxonomy verbs

    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
    Not in Any Lists

    No Comments

    Negative Logits
    íns
    0.29
     createArticle
    0.26
    Bep
    0.26
    ERICK
    0.26
    oclaw
    0.26
    蛸
    0.26
     ფედერ
    0.25
    лә
    0.24
    歴史
    0.24
    FUN
    0.24
    POSITIVE LOGITS
     Dos
    0.25
     เว
    0.24
     ge
    0.24
     DOI
    0.24
     S
    0.23
     আভ
    0.23
     Franz
    0.23
    cede
    0.23
     H
    0.22
     Vaccination
    0.22
    Activations Density 0.000%

    No Known Activations