© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51504
    Prev
    Next
    INDEX
    Explanations

    "I" followed by punctuation or "can"

    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_10_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
     legislación
    0.46
    ير
    0.43
     оголо
    0.43
     κοινων
    0.43
    诺
    0.42
     даних
    0.42
     фарма
    0.41
     عندنا
    0.41
     convulsions
    0.41
     أو
    0.41
    POSITIVE LOGITS
    ina
    0.53
    st
    0.52
    ă
    0.48
    İ
    0.48
    ha
    0.48
    Ə
    0.48
     The
    0.47
    ė
    0.47
    se
    0.47
     pentru
    0.47
    Activations Density 0.031%

    No Known Activations