Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11228
    Prev
    Next
    INDEX
    Explanations

    common words such as "the," "is," "of," "to," and "a."

    oai_token-act-pair · gemini-2.0-flash

    terms related to device modifications

    np_token-act-pair-logits · gpt-4o-mini

    modifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     caras
    -0.48
     genoux
    -0.48
    arrol
    -0.48
     faccia
    -0.47
     planas
    -0.45
     scolaires
    -0.44
     buoni
    -0.44
     épaules
    -0.42
     normaux
    -0.42
     colorés
    -0.42
    POSITIVE LOGITS
     modification
    0.96
     modifications
    0.94
     Modification
    0.90
     conversions
    0.88
     Modifications
    0.87
     retrofit
    0.87
     additions
    0.86
     modify
    0.86
     conversion
    0.85
     install
    0.85
    Activations Density 3.471%

    No Known Activations