© 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. 165165
    Prev
    Next
    INDEX
    Explanations

    output / input

    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
    к
    0.37
    क
    0.35
    onym
    0.35
     k
    0.34
     m
    0.34
    m
    0.34
    ک
    0.34
    arin
    0.33
    iken
    0.33
     ла
    0.33
    POSITIVE LOGITS
    🚴
    0.36
    nicht
    0.35
    ╕
    0.35
     ;-)
    0.33
     muchachos
    0.33
    খ্যাত
    0.32
    🚂
    0.32
     squadron
    0.31
     bhikkhu
    0.31
     tenéis
    0.31
    Activations Density 0.076%

    No Known Activations