© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203108
    Prev
    Next
    INDEX
    Explanations

    pronoun 'it' followed by punctuation or conjunctions

    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_6_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
     paramet
    0.93
     distrib
    0.90
     estamp
    0.83
     يستخدم
    0.82
    คุณ
    0.81
     Ι
    0.80
     alkohol
    0.80
     הראש
    0.79
     وب
    0.79
    ри
    0.78
    POSITIVE LOGITS
    to
    1.42
    the
    1.06
    be
    1.02
    dır
    1.02
    d
    1.01
    ו
    0.95
    of
    0.94
    '
    0.92
    in
    0.91
    their
    0.91
    Activations Density 0.004%

    No Known Activations