© 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. 38192
    Prev
    Next
    INDEX
    Explanations

    foundational element or concept

    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
     such
    0.67
     $\{
    0.63
    ,​
    0.62
    ୫
    0.62
     ഇത്തരം
    0.62
    supportsFocus
    0.60
    ୩
    0.59
     SUCH
    0.58
     стрелецкой
    0.57
    ​,
    0.57
    POSITIVE LOGITS
    o
    0.57
    Been
    0.57
    する必要があります
    0.55
    ركه
    0.55
     empresa
    0.54
    TB
    0.53
    یی
    0.53
    RU
    0.52
    ir
    0.52
    OU
    0.50
    Activations Density 0.006%

    No Known Activations