© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149802
    Prev
    Next
    INDEX
    Explanations

    programming or data terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     north
    0.54
     This
    0.45
     west
    0.44
     nel
    0.44
     northern
    0.43
     c
    0.42
     crescent
    0.41
     ó
    0.41
     northwest
    0.41
     Questo
    0.41
    POSITIVE LOGITS
    r
    0.96
    t
    0.91
    n
    0.86
    rs
    0.84
    o
    0.84
    g
    0.82
    l
    0.80
    d
    0.80
    m
    0.78
    e
    0.75
    Activations Density 0.003%

    No Known Activations