© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83372
    Prev
    Next
    INDEX
    Explanations

    cust and COVID

    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_0_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
    та
    1.87
    ма
    1.75
    да
    1.74
    ק
    1.66
    ก
    1.65
    ے
    1.59
    נ
    1.58
    с
    1.54
    к
    1.54
    н
    1.50
    POSITIVE LOGITS
    0
    1.60
    al
    1.49
     I
    1.48
    ード
    1.38
     for
    1.38
    em
    1.37
    kost
    1.33
    e
    1.33
     by
    1.32
    i
    1.32
    Activations Density 0.000%

    No Known Activations