Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14355
    Prev
    Next
    INDEX
    Explanations

    text relating to the invention, usage, and components of curtain rods

    oai_token-act-pair · gemini-2.0-flash

    curtains and windows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.56
    RectangleBorder
    -0.54
    tencent
    -0.51
    finity
    -0.50
     '{@
    -0.49
    ViewFeatures
    -0.49
     ComVisible
    -0.49
    رشف
    -0.49
     MainAxisSize
    -0.49
     Bailly
    -0.48
    POSITIVE LOGITS
    BeanUtils
    0.50
     val
    0.48
     dam
    0.48
    ‭
    0.47
    ISES
    0.47
     Réponses
    0.47
    voix
    0.47
     indirect
    0.47
    Ranks
    0.46
    graphicx
    0.46
    Activations Density 0.774%

    No Known Activations