© 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
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11709
    Prev
    Next
    INDEX
    Explanations

    location and area/money

    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_13_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
    ání
    0.33
    getTotal
    0.32
     sơ
    0.32
     (/
    0.30
    蹈
    0.30
    qat
    0.30
     রস
    0.29
     production
    0.29
    QA
    0.29
     oath
    0.29
    POSITIVE LOGITS
     বৃহৎ
    0.35
     ключе
    0.34
     даже
    0.32
    ektiv
    0.32
     addirittura
    0.32
     μεγά
    0.32
     зру
    0.32
    cev
    0.31
     уют
    0.31
    狨
    0.31
    Activations Density 0.069%

    No Known Activations