© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165099
    Prev
    Next
    INDEX
    Explanations

    oil and companies

    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_13_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
    泮
    0.52
     atthe
    0.51
     අධ
    0.49
     බොහෝ
    0.49
    Shanghai
    0.48
    ↵↵↵↵
    0.48
    !',
    0.48
    lni
    0.48
     ovoj
    0.48
    drž
    0.47
    POSITIVE LOGITS
     factor
    0.60
     artistic
    0.60
     protectors
    0.60
     pastime
    0.58
     collar
    0.57
    u
    0.57
     agonist
    0.56
     accessories
    0.56
     necrosis
    0.56
     artists
    0.55
    Activations Density 0.009%

    No Known Activations