© 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. 173830
    Prev
    Next
    INDEX
    Explanations

    if that's

    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
     criteria
    0.45
    Criteria
    0.45
     elemen
    0.44
    StudentID
    0.44
     courtes
    0.43
     przypad
    0.43
    Elem
    0.42
    ﾎ
    0.42
     supremacy
    0.42
    ㈣
    0.42
    POSITIVE LOGITS
     नई
    0.52
     आत्मनिर्भर
    0.52
     ότι
    0.49
     Compare
    0.46
     że
    0.46
     एप्लिकेशन
    0.46
    是一家
    0.45
     तेज
    0.45
     Rent
    0.45
     बदल
    0.44
    Activations Density 0.001%

    No Known Activations