© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    words related to size, weight, and materials.

    oai_token-act-pair · gemini-2.0-flash

    Incomplete/raw state

    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
    IUrlHelper
    -0.79
    WebElementEntity
    -0.79
     '\\;'
    -0.77
    новништво
    -0.76
     تانيه
    -0.76
    DoubleQuotes
    -0.75
     فريبيس
    -0.75
    AutoresizingMask
    -0.73
    脚注の使い方
    -0.73
     مشين
    -0.72
    POSITIVE LOGITS
     un
    1.05
     raw
    0.98
     fully
    0.91
     empty
    0.86
     unloaded
    0.82
    raw
    0.79
     bare
    0.79
     dry
    0.77
     clean
    0.70
     Fully
    0.70
    Activations Density 3.561%

    No Known Activations