© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107114
    Prev
    Next
    INDEX
    Explanations

    underemployment, underrepresentation, underqualified, undercutting

    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_1_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
    '
    1.81
     a
    1.64
    ',
    1.09
     it
    1.07
    '،
    1.07
    ด์
    1.02
    oma
    1.02
    orems
    0.99
    izers
    0.98
    ielle
    0.95
    POSITIVE LOGITS
    р
    1.54
    ar
    1.52
    al
    1.43
    r
    1.39
    ר
    1.39
    ad
    1.30
    il
    1.21
    d
    1.20
    ر
    1.20
    ર
    1.15
    Activations Density 0.003%

    No Known Activations