© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193442
    Prev
    Next
    INDEX
    Explanations

    independent contractors

    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_4_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
    es
    1.51
    em
    1.22
    ed
    1.18
    an
    1.05
    a
    0.98
    rés
    0.96
    zelfde
    0.95
    يون
    0.94
    arz
    0.92
    e
    0.92
    POSITIVE LOGITS
     in
    1.20
    ta
    0.77
    (
    0.72
    ’
    0.71
     University
    0.68
    کس
    0.67
     deportation
    0.67
     RICO
    0.66
    在
    0.66
    ִי
    0.64
    Activations Density 0.001%

    No Known Activations