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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14706
    Prev
    Next
    INDEX
    Explanations

    words that probably occur in code and/or the conjunction "and"

    oai_token-act-pair · gemini-2.0-flash

    "and" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Autoritní
    -0.80
    SBATCH
    -0.75
    <bos>
    -0.73
    
    -0.73
    :+:
    -0.71
    BASEPATH
    -0.71
    éez
    -0.69
     convertView
    -0.69
    gdx
    -0.67
    leville
    -0.67
    POSITIVE LOGITS
    /
    0.91
     therefore
    0.59
    Therefore
    0.45
    therefore
    0.44
    most
    0.44
     thus
    0.43
    romeda
    0.42
     dermed
    0.42
     ezért
    0.42
    /(
    0.42
    Activations Density 0.639%

    No Known Activations