© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118075
    Prev
    Next
    INDEX
    Explanations

    exceptions to descriptions

    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_27_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
     दृश्य
    0.34
     Appear
    0.30
    apparent
    0.30
    𝑵
    0.30
    隠
    0.30
    opuerto
    0.30
    รีย
    0.29
     visibly
    0.29
    显
    0.29
     Mention
    0.29
    POSITIVE LOGITS
     belangrijkste
    0.32
     faire
    0.32
    ilihan
    0.30
     wichtigsten
    0.29
     faceted
    0.29
    Chois
    0.29
     integrity
    0.29
    㿝
    0.29
    Javadoc
    0.28
    integrity
    0.28
    Activations Density 0.011%

    No Known Activations