© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92205
    Prev
    Next
    INDEX
    Explanations

    paving the way for

    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_11_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
    نوان
    0.54
    的表现
    0.54
    Information
    0.54
    的关键
    0.54
    的代码
    0.54
    க்கவும்
    0.53
    ссер
    0.52
    <unused477>
    0.51
    olev
    0.50
     সংগ্রামী
    0.50
    POSITIVE LOGITS
    點
    0.62
    约定
    0.57
     distanza
    0.56
     مَا
    0.56
     apartamentos
    0.55
     racconta
    0.54
    距离
    0.53
     landslides
    0.53
    調理
    0.52
    mette
    0.52
    Activations Density 0.000%

    No Known Activations