© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101322
    Prev
    Next
    INDEX
    Explanations

    Company names, including Allianz SE

    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_14_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
    GREAT
    0.55
    (**
    0.54
    DIE
    0.54
    et
    0.52
    ■
    0.52
    基本的
    0.48
    Глав
    0.48
    ngths
    0.47
    a
    0.47
    MIL
    0.47
    POSITIVE LOGITS
     عص
    0.48
     ευ
    0.48
    SearchCV
    0.47
    에서도
    0.47
    äch
    0.46
    Š
    0.46
     vicenda
    0.46
     ਭ
    0.46
     सशक्त
    0.45
     متر
    0.45
    Activations Density 0.000%

    No Known Activations