© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57874
    Prev
    Next
    INDEX
    Explanations

    months of year

    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
     ย
    0.60
     य
    0.55
     Y
    0.54
    Y
    0.54
     y
    0.53
    StartY
    0.53
     ی
    0.52
    ้ย
    0.49
     ય
    0.48
    <0xA1>
    0.46
    POSITIVE LOGITS
     June
    1.69
     December
    1.60
     September
    1.55
     March
    1.52
    June
    1.50
    December
    1.39
    September
    1.32
    March
    1.30
     DECEMBER
    1.20
     JUNE
    1.20
    Activations Density 0.000%

    No Known Activations