© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179383
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Easier
    0.35
    imi
    0.35
    菏
    0.34
    HDMI
    0.34
    IMI
    0.32
     greatest
    0.32
    堪
    0.32
     Greatest
    0.32
    된
    0.32
    icono
    0.32
    POSITIVE LOGITS
     more
    2.00
    more
    1.72
     mehr
    1.60
     más
    1.52
     أكثر
    1.49
     lebih
    1.45
     более
    1.45
     więcej
    1.41
     MORE
    1.39
    More
    1.38
    Activations Density 0.002%

    No Known Activations