© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257828
    Prev
    Next
    INDEX
    Explanations

    produced from, put the, include alcoholic

    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_22_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
                              
    0.44
    staande
    0.44
    setHorizontal
    0.40
                           
    0.39
    <thead>
    0.39
     வழங்கப்படும்
    0.39
    lof
    0.39
     bounded
    0.38
     Vidal
    0.38
    alla
    0.38
    POSITIVE LOGITS
    рами
    0.46
    ють
    0.39
     описы
    0.39
     rashes
    0.39
     bilgi
    0.39
    ડો
    0.38
    인데
    0.38
     چاہتے
    0.38
     самих
    0.38
    蚁
    0.38
    Activations Density 0.016%

    No Known Activations