© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112620
    Prev
    Next
    INDEX
    Explanations

    pronoun

    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_2_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
    ।
    1.75
    al
    1.57
    can
    1.48
     can
    1.47
    。
    1.46
    ד
    1.29
    ۔
    1.23
    s
    1.22
    p
    1.19
    ן
    1.15
    POSITIVE LOGITS
     posteriores
    1.19
     emocion
    1.16
    čných
    1.15
    ка
    1.13
     νέα
    1.12
     fáciles
    1.11
    ത്
    1.08
    ám
    1.07
     clás
    1.07
    很
    1.07
    Activations Density 0.001%

    No Known Activations