© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227381
    Prev
    Next
    INDEX
    Explanations

    GarageBand, bathroom trips, kitchen

    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_6_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
    x
    0.89
     abril
    0.82
    k
    0.79
     allemand
    0.77
     for
    0.75
    z
    0.70
     and
    0.70
    ພວກເຮົາ
    0.69
     arabe
    0.69
    ut
    0.68
    POSITIVE LOGITS
    만
    0.59
     connector
    0.59
     pathway
    0.58
     multiport
    0.57
    是
    0.57
     contaminant
    0.57
     circumference
    0.57
     convolution
    0.56
    에
    0.56
    源
    0.56
    Activations Density 0.002%

    No Known Activations