© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125757
    Prev
    Next
    INDEX
    Explanations

    names, Charlotte, Peters, Paula, Lemb, University, fibrosus

    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_3_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
    in
    0.92
    p
    0.77
    n
    0.69
    ar
    0.68
    g
    0.66
    ell
    0.63
    at
    0.62
    l
    0.61
    b
    0.61
    one
    0.61
    POSITIVE LOGITS
    ва
    0.72
     labored
    0.71
    ’
    0.68
    ية
    0.66
     bulunduğu
    0.66
     impactos
    0.64
     tattooed
    0.62
     डाउट्स
    0.62
     wrestled
    0.62
     efeito
    0.61
    Activations Density 0.000%

    No Known Activations