© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51113
    Prev
    Next
    INDEX
    Explanations

    pytest and cmake

    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_10_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
    :
    0.95
    h
    0.79
    db
    0.70
    /
    0.68
    b
    0.65
     Human
    0.63
     human
    0.62
    the
    0.60
    ala
    0.60
    FileWriter
    0.60
    POSITIVE LOGITS
     işaret
    0.84
    тор
    0.84
     advertise
    0.82
     оно
    0.82
     mạch
    0.81
    ير
    0.80
     oppose
    0.78
     ४
    0.78
     이라고
    0.78
     advertisements
    0.75
    Activations Density 0.003%

    No Known Activations