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. 13962
    Prev
    Next
    INDEX
    Explanations

    emotionally charged argumentative statements or opinions.

    oai_token-act-pair · gemini-2.0-flash

    negative comments/disagreements

    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
    -0.90
     oprot
    -0.85
    OGND
    -0.83
    بوابة
    -0.76
     متعلقه
    -0.76
     HasFactory
    -0.75
    mybatisplus
    -0.75
     otomatig
    -0.75
    SerializedSize
    -0.73
    ViewFeatures
    -0.73
    POSITIVE LOGITS
    itoba
    0.40
     supposes
    0.40
     вижу
    0.38
    gmd
    0.38
     commentaries
    0.38
     frescoes
    0.36
     sign
    0.36
     comments
    0.35
     emot
    0.35
     greifen
    0.35
    Activations Density 3.545%

    No Known Activations