© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164311
    Prev
    Next
    INDEX
    Explanations

    employees' job status and dates

    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_13_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
    )
    0.59
    ,
    0.57
    ،
    0.56
    um
    0.54
    et
    0.50
     Bases
    0.50
    :
    0.49
    ，
    0.49
    ।
    0.48
    `
    0.47
    POSITIVE LOGITS
     varit
    0.56
     Saltar
    0.55
     Förder
    0.54
     शब्द
    0.52
     Shabbat
    0.51
    ahraga
    0.50
     utbild
    0.50
    溆
    0.50
    рім
    0.50
     employment
    0.49
    Activations Density 0.023%

    No Known Activations