© 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. 4466
    Prev
    Next
    INDEX
    Explanations

    LaTeX, code, and URLs

    oai_token-act-pair · gemini-2.0-flash

    computer code

    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
     change
    -1.40
     Change
    -1.17
    change
    -1.16
    Change
    -1.09
     cambio
    -1.04
     CHANGE
    -1.02
    CHANGE
    -0.92
     changes
    -0.86
     mudança
    -0.84
     changed
    -0.84
    POSITIVE LOGITS
    istoitu
    0.69
    tagHelperRunner
    0.65
    )));
    0.61
    Autoritní
    0.60
     }}$}
    0.57
    setVerticalGroup
    0.57
     estimés
    0.57
    TagMode
    0.56
    ))
    0.54
     consultato
    0.54
    Activations Density 17.136%

    No Known Activations