© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets and chemical formulas

    oai_token-act-pair · gemini-2.0-flash

    chemical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    GraphicsUnit
    -0.96
    
    -0.84
     chi̍t
    -0.81
    RectangleBorder
    -0.72
     FetchType
    -0.67
    findpost
    -0.67
     يتيمه
    -0.66
     NSCoder
    -0.62
    WebServlet
    -0.60
    tableFuture
    -0.60
    POSITIVE LOGITS
     stands
    0.50
    ATURE
    0.50
    stood
    0.50
    ligi
    0.49
     Car
    0.47
    笠
    0.46
    phoria
    0.46
     existência
    0.46
    ding
    0.45
    dessus
    0.45
    Activations Density 2.055%

    No Known Activations