© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11020
    Prev
    Next
    INDEX
    Explanations

    cooling or liquid partnership

    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
     رفت
    0.53
     ሃ
    0.51
    ปรับ
    0.49
     cambiato
    0.48
     revisions
    0.48
     измени
    0.47
    itability
    0.47
     adaptive
    0.47
     попы
    0.46
     تغییر
    0.46
    POSITIVE LOGITS
     الك
    0.51
     Portugal
    0.50
     Varan
    0.50
    湳
    0.49
     Postgres
    0.48
    http
    0.48
     Microbial
    0.48
     नाबाल
    0.48
     Alcat
    0.48
     Turtles
    0.47
    Activations Density 0.010%

    No Known Activations