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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1068
    Prev
    Next
    INDEX
    Explanations

    phrases related to the New York Giants football team and scientific/medical terms

    oai_token-act-pair · gemini-2.0-flash

    rush

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    posedge
    -0.59
    <bos>
    -0.55
    tituted
    -0.52
    ïsme
    -0.50
    ToLeft
    -0.50
    olong
    -0.50
    נח
    -0.50
    웃
    -0.50
    Resources
    -0.49
    tière
    -0.49
    POSITIVE LOGITS
    تقاوى
    0.65
    complexContent
    0.57
     ***!
    0.55
    ⓧ
    0.53
     الحره
    0.52
    TypedDataSet
    0.49
    TagMode
    0.48
    CopyWith
    0.47
    Демографія
    0.47
     للاسماء
    0.44
    Activations Density 2.921%

    No Known Activations