© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201478
    Prev
    Next
    INDEX
    Explanations

    Standard and Deluxe room types

    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_12_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
    0
    0.66
    educational
    0.56
    peas
    0.55
    analog
    0.55
     intolerant
    0.55
    5
    0.54
    und
    0.54
    änden
    0.53
    ppes
    0.52
    international
    0.52
    POSITIVE LOGITS
    เร
    0.54
    買い
    0.52
     గారి
    0.52
     décès
    0.50
    來
    0.47
     calcular
    0.47
     KEEP
    0.47
    Keep
    0.46
    Ꭱ
    0.46
     месяца
    0.46
    Activations Density 0.000%

    No Known Activations