© 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. 38832
    Prev
    Next
    INDEX
    Explanations

    historical eras and places

    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
    \
    0.88
    -
    0.83
     metastases
    0.71
     shameful
    0.70
    \;\
    0.70
    트
    0.66
    ت
    0.66
     necessidades
    0.65
    ления
    0.64
     prizes
    0.64
    POSITIVE LOGITS
    نا
    0.87
    know
    0.63
    әт
    0.61
    raises
    0.58
    iles
    0.57
    搁
    0.57
    ומי
    0.57
    cough
    0.57
    differ
    0.55
    each
    0.54
    Activations Density 0.017%

    No Known Activations