© 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. 89048
    Prev
    Next
    INDEX
    Explanations

    HDFS path to file

    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
    '
    1.27
    ag
    0.96
    ong
    0.95
    ick
    0.91
    itt
    0.90
    ing
    0.84
    em
    0.80
    ika
    0.79
    ain
    0.78
    ak
    0.75
    POSITIVE LOGITS
    ו
    1.13
    ي
    1.09
    و
    1.05
    ли
    1.04
    И
    0.88
    I
    0.87
    ق
    0.82
    트
    0.80
    При
    0.78
    이
    0.78
    Activations Density 0.001%

    No Known Activations