© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218510
    Prev
    Next
    INDEX
    Explanations

    property and real estate

    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_47_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
    놓
    0.41
    十二
    0.39
    轰
    0.38
    递
    0.38
    ુદ્ધ
    0.36
     বিশ্বকাপ
    0.35
     IEEE
    0.35
    Sophia
    0.35
    Principal
    0.35
    Twelve
    0.35
    POSITIVE LOGITS
     ड्राई
    0.42
     acrylate
    0.41
    Boost
    0.40
    เร็จ
    0.40
    adType
    0.40
    ⼒
    0.39
    acry
    0.39
    荲
    0.38
    (\
    0.38
     complic
    0.38
    Activations Density 0.000%

    No Known Activations