© 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. 6715
    Prev
    Next
    INDEX
    Explanations

    positive sentiment with some occurrences of the word "be" or the letter "I"

    oai_token-act-pair · gemini-2.0-flash

    usefulness

    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
     useful
    -2.17
     Useful
    -2.14
    Useful
    -2.03
    useful
    -2.03
     practical
    -1.73
     utile
    -1.70
    Practical
    -1.70
     helpful
    -1.64
     Practical
    -1.62
    practical
    -1.60
    POSITIVE LOGITS
    ArrowToggle
    0.91
    hésite
    0.70
    ,:);
    0.69
    ConstraintMaker
    0.66
    readystatechange
    0.66
    SBATCH
    0.63
    DatabaseError
    0.63
     cesse
    0.61
     mariée
    0.61
    LEncoder
    0.61
    Activations Density 2.821%

    No Known Activations