© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18937
    Prev
    Next
    INDEX
    Explanations

    the more

    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_40_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
     Lour
    0.38
    FlagSet
    0.37
    鏤
    0.36
    स्कृत
    0.34
    स्वर
    0.33
    oksatta
    0.33
    तुरंग
    0.33
    Dlg
    0.32
    EXPECT
    0.32
    }}$,
    0.32
    POSITIVE LOGITS
     fewer
    1.59
     more
    1.52
     faster
    1.44
     harder
    1.42
     greater
    1.41
     better
    1.38
     stronger
    1.34
     quicker
    1.33
     easier
    1.32
     أكثر
    1.32
    Activations Density 0.077%

    No Known Activations