© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 58104
    Prev
    Next
    INDEX
    Explanations

    first person pronoun "I"

    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_11_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
    ’
    0.73
    '
    0.71
     de
    0.70
     are
    0.66
    C
    0.64
    Chick
    0.62
    ό
    0.62
    ки
    0.59
    l
    0.59
     has
    0.58
    POSITIVE LOGITS
     کنم
    0.66
     منطقه
    0.61
    tugraz
    0.59
    )|\
    0.59
    }$).
    0.59
    ก็จะ
    0.58
     المنطقة
    0.57
     المستوى
    0.57
     Runtime
    0.56
    cnty
    0.55
    Activations Density 0.150%

    No Known Activations