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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198844
    Prev
    Next
    INDEX
    Explanations

    code structures

    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_15_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
    haft
    0.21
    ℉
    0.19
    Denovo
    0.18
    ीकृत
    0.18
     baseY
    0.18
    旂
    0.17
     gewährleisten
    0.17
    失去
    0.17
     പിന്തുണ
    0.17
    œuvre
    0.17
    POSITIVE LOGITS
    s
    0.25
    r
    0.22
    َل
    0.21
    p
    0.21
    lt
    0.21
    rl
    0.20
    pt
    0.19
     ভূমিক
    0.19
     उन्‍हें
    0.19
    ip
    0.19
    Activations Density 0.003%

    No Known Activations