© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4772
    Prev
    Next
    INDEX
    Explanations

    dog owner, canine, enrichment

    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_39_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
    拧
    0.35
    ebi
    0.35
     Sagan
    0.35
     sourire
    0.33
     plug
    0.31
    గు
    0.31
    ებას
    0.31
     кара
    0.31
    emias
    0.31
    тами
    0.31
    POSITIVE LOGITS
     dogs
    0.51
     enrichment
    0.49
     Enrichment
    0.49
     canine
    0.48
    犬
    0.47
     犬
    0.46
     kennel
    0.44
     hous
    0.44
     hound
    0.44
     hunde
    0.43
    Activations Density 0.175%

    No Known Activations