© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4578
    Prev
    Next
    INDEX
    Explanations

    baby related items

    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_39_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
    志
    0.35
     Thousands
    0.35
    udem
    0.34
    話
    0.34
     क्लो
    0.33
     protop
    0.32
    чам
    0.32
     정신
    0.32
    丽
    0.32
     Lydia
    0.32
    POSITIVE LOGITS
    arrival
    0.35
    cules
    0.34
     mom
    0.34
     bamboo
    0.34
     Merlot
    0.34
    vic
    0.33
     clocks
    0.33
     arrival
    0.33
     Elders
    0.33
    adolid
    0.32
    Activations Density 0.023%

    No Known Activations