© 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. 29975
    Prev
    Next
    INDEX
    Explanations

    add followed by article or 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_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
     iš
    0.57
    工资
    0.56
     ").
    0.55
    ㅅ
    0.53
    점
    0.52
    菪
    0.52
    ༸
    0.52
    ING
    0.52
    ເມ
    0.52
     ऑफ़
    0.51
    POSITIVE LOGITS
    ل
    0.71
    in
    0.66
    ن
    0.64
    et
    0.64
    ar
    0.63
    ado
    0.63
    و
    0.61
    م
    0.61
    im
    0.60
    ert
    0.59
    Activations Density 0.027%

    No Known Activations