© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 324
    Prev
    Next
    INDEX
    Explanations

    manifest.json keys

    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_40_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
     образова
    0.47
    လုံး
    0.42
    텟
    0.42
     ישראל
    0.39
    ल्लभ
    0.39
    Doe
    0.39
    Educational
    0.38
    हेज
    0.38
    benhav
    0.38
    ൦
    0.38
    POSITIVE LOGITS
     react
    0.45
     React
    0.43
    extend
    0.41
     expanded
    0.41
    React
    0.40
     whole
    0.40
     entirety
    0.39
     Ultra
    0.38
     REACT
    0.38
     joint
    0.38
    Activations Density 0.001%

    No Known Activations