© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194574
    Prev
    Next
    INDEX
    Explanations

    Capital Gains

    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
    ль
    0.17
    ě
    0.15
    ู
    0.15
    s
    0.14
    ې
    0.14
    ى
    0.14
    sa
    0.13
    تی
    0.13
    surgery
    0.12
    اب
    0.12
    POSITIVE LOGITS
     allemand
    0.14
    Thời
    0.14
     ומ
    0.14
     enzym
    0.13
     IMEI
    0.13
     IGBT
    0.13
     eventuali
    0.13
    тят
    0.13
     specif
    0.13
     ODBC
    0.13
    Activations Density 0.002%

    No Known Activations