© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14579
    Prev
    Next
    INDEX
    Explanations

    words describing people in conflict

    oai_token-act-pair · gemini-2.0-flash

    escaping or leaving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Lähteet
    -0.44
     Corintios
    -0.44
     minced
    -0.43
     pimienta
    -0.42
     hoogte
    -0.41
     naturale
    -0.41
     bivolt
    -0.41
     damska
    -0.40
     northward
    -0.40
     orchids
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.81
    ########.
    0.79
     виправивши
    0.76
    DoubleQuotes
    0.73
    mybatisplus
    0.72
    HtmlAttribute
    0.70
    ollectionView
    0.70
    setVerticalGroup
    0.68
    prepareStatement
    0.68
    RenderAtEndOf
    0.66
    Activations Density 3.279%

    No Known Activations