© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180471
    Prev
    Next
    INDEX
    Explanations

    applying a rule or reason

    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
     predomin
    0.35
     desk
    0.34
     "
    0.33
     investigate
    0.31
     Soybean
    0.30
     Component
    0.30
     «
    0.29
    ल्टी
    0.29
    ピング
    0.29
    त्रेयी
    0.29
    POSITIVE LOGITS
     nepř
    0.40
    Begriff
    0.36
     oluşan
    0.36
     sebab
    0.36
     фла
    0.36
     entusias
    0.35
     adhipp
    0.35
     nhỏ
    0.34
    çamento
    0.34
    齢
    0.34
    Activations Density 0.003%

    No Known Activations