© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46234
    Prev
    Next
    INDEX
    Explanations

    IP, LTE, SSL, HTTPS, dinner, time

    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_3_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
    )।
    0.77
    াম
    0.72
    ার
    0.67
     സ
    0.66
    ।”
    0.64
    ुत
    0.64
    ।)
    0.64
    >∕
    0.63
    September
    0.63
     ریک
    0.62
    POSITIVE LOGITS
    ский
    1.03
    يدة
    0.86
    S
    0.82
    спользова
    0.75
    ية
    0.74
    ق
    0.73
    ضع
    0.73
    할
    0.72
    بي
    0.71
    ственный
    0.71
    Activations Density 0.002%

    No Known Activations