© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9926
    Prev
    Next
    INDEX
    Explanations

    department or program affiliation

    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_13_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
     atuação
    0.37
     counteract
    0.34
     reorgan
    0.31
    하도록
    0.31
    㨁
    0.30
     সেনাবাহিনীকে
    0.30
    点评
    0.30
     subdue
    0.30
     subdiv
    0.30
    🔅
    0.30
    POSITIVE LOGITS
    g
    0.40
    k
    0.36
    u
    0.34
    ก
    0.30
    j
    0.29
    q
    0.29
    夔
    0.29
    uir
    0.29
    qe
    0.29
    o
    0.29
    Activations Density 0.022%

    No Known Activations