© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 13942
    Prev
    Next
    INDEX
    Explanations

    technical or academic language, including code snippets, references, and specific vocabulary from various fields such as physics, data analysis, or medicine.

    oai_token-act-pair · gemini-2.0-flash

    Code, documentation, database queries

    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
     **)
    -0.63
     $]$
    -0.63
    ))));
    -0.63
    )]
    
    -0.62
    .'”
    -0.60
     $)$
    -0.59
    >");
    
    -0.57
    >");
    -0.57
    .'"
    -0.57
    msgTypes
    -0.57
    POSITIVE LOGITS
    findpost
    0.69
    0
    0.68
    5
    0.60
    RenderAtEndOf
    0.59
    #+#
    0.58
     propOrder
    0.57
    2
    0.57
    7
    0.56
    4
    0.56
    glGen
    0.54
    Activations Density 13.230%

    No Known Activations