© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 180531
    Prev
    Next
    INDEX
    Explanations

    street address components

    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_29_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
    社の
    0.29
    周边
    0.29
     शरद
    0.28
     beds
    0.27
    liery
    0.27
    允
    0.27
     वाहन
    0.27
     பகுதிகளில்
    0.27
    千萬
    0.27
     automobiles
    0.27
    POSITIVE LOGITS
     선생님
    0.28
     沖縄
    0.28
    Cou
    0.28
     Uygh
    0.28
     quaerat
    0.27
    (_
    0.27
     cou
    0.27
     proficient
    0.27
     אטאטורק
    0.27
     linguistics
    0.26
    Activations Density 0.006%

    No Known Activations