© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36755
    Prev
    Next
    INDEX
    Explanations

    Old English history

    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
    보는
    0.66
    ться
    0.66
     diem
    0.66
    тор
    0.62
    '
    0.58
     diode
    0.58
     από
    0.57
     débil
    0.57
     productColor
    0.57
    стром
    0.56
    POSITIVE LOGITS
     that
    0.86
    that
    0.70
    ا
    0.69
    n
    0.68
    ために
    0.67
    I
    0.63
    ن
    0.61
    uris
    0.60
    ためには
    0.60
    مان
    0.59
    Activations Density 0.002%

    No Known Activations