© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4314
    Prev
    Next
    INDEX
    Explanations

    em followed by common words

    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
     දි
    0.37
    roweak
    0.36
    ោគ
    0.36
    sville
    0.36
     avviene
    0.36
    avises
    0.36
    거운
    0.36
    餾
    0.36
    ᱜ
    0.35
    iosity
    0.35
    POSITIVE LOGITS
     Em
    0.68
    Em
    0.63
     emuls
    0.61
     Emory
    0.58
     em
    0.55
     emulator
    0.54
     ema
    0.52
     emulsion
    0.52
     embol
    0.52
     Emulator
    0.52
    Activations Density 0.035%

    No Known Activations