© 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. 10407
    Prev
    Next
    INDEX
    Explanations

    location indicators

    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
     Underwater
    0.30
     Things
    0.30
     Solutions
    0.29
    Subjects
    0.29
    Solutions
    0.29
    as
    0.28
    Interest
    0.28
    m
    0.28
    מ
    0.28
    ']
    0.28
    POSITIVE LOGITS
    ಧಾನ
    0.30
     yarg
    0.29
    itudine
    0.29
     chamado
    0.28
     abo
    0.27
     जो
    0.27
     commanding
    0.27
     wrought
    0.27
     brutally
    0.26
     ktorí
    0.26
    Activations Density 0.042%

    No Known Activations