© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122763
    Prev
    Next
    INDEX
    Explanations

    brooklyn/queens locations

    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
    util
    0.68
    อบ
    0.68
    0.67
    Country
    0.66
    A
    0.66
    T
    0.65
    H
    0.65
    Or
    0.64
    Green
    0.63
    C
    0.63
    POSITIVE LOGITS
    {
    0.79
     enti
    0.69
    ча
    0.68
     répart
    0.68
     trapping
    0.67
     maliciously
    0.67
     в
    0.66
     độ
    0.66
     abode
    0.66
     empresarios
    0.65
    Activations Density 0.000%

    No Known Activations