© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42274
    Prev
    Next
    INDEX
    Explanations

    would + verb / auxiliary

    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_3_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
    u
    0.84
    忥
    0.68
    k
    0.67
    да
    0.67
    itemize
    0.65
    из
    0.65
    عند
    0.65
    ز
    0.65
    ф
    0.65
    клар
    0.63
    POSITIVE LOGITS
     I
    0.77
     pilote
    0.68
     comte
    0.65
     término
    0.65
     pruž
    0.62
     precedente
    0.61
     Poder
    0.61
     recipiente
    0.61
     permesso
    0.60
     potere
    0.59
    Activations Density 0.004%

    No Known Activations