© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208768
    Prev
    Next
    INDEX
    Explanations

    articles before nouns

    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_20_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
    หาร
    0.35
     gift
    0.35
     clover
    0.35
     hogs
    0.35
     frozen
    0.34
     discovery
    0.34
     miracle
    0.34
    狞
    0.33
     buck
    0.33
     master
    0.32
    POSITIVE LOGITS
     Spagna
    0.40
    ega
    0.40
    ũ
    0.39
    onia
    0.39
    ambia
    0.39
    atio
    0.38
     Marta
    0.37
    onin
    0.37
     Differences
    0.37
     differenza
    0.37
    Activations Density 0.004%

    No Known Activations