© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34369
    Prev
    Next
    INDEX
    Explanations

    people's names and organizations

    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_3_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
    an
    0.87
    in
    0.72
    ar
    0.72
     sufr
    0.61
    E
    0.61
    ிர்
    0.60
    hotels
    0.59
     bebidas
    0.59
    aný
    0.59
    et
    0.58
    POSITIVE LOGITS
    ้ง
    0.61
     \
    0.59
    $
    0.59
    ت
    0.59
    телем
    0.57
    ke
    0.55
    ंकज
    0.55
    ية
    0.53
    我们
    0.53
    ্যাম
    0.52
    Activations Density 0.004%

    No Known Activations