© 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. 126218
    Prev
    Next
    INDEX
    Explanations

    pronoun "they" followed by verb

    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
     that
    0.82
    w
    0.82
     who
    0.80
     of
    0.73
     E
    0.72
     ﺍ
    0.68
     U
    0.68
     EditText
    0.67
    2
    0.67
     REI
    0.66
    POSITIVE LOGITS
    are
    0.66
    大
    0.66
    情况下
    0.62
     ہوگی
    0.62
    心
    0.62
    für
    0.61
    事例
    0.61
    daki
    0.60
    ある
    0.59
    வ்வேறு
    0.59
    Activations Density 0.001%

    No Known Activations