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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7704
    Prev
    Next
    INDEX
    Explanations

    language that indicates negative sentiment toward a person or group of people.

    oai_token-act-pair · gemini-2.0-flash

    like/such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     كورة
    -0.65
     fermés
    -0.58
     varandra
    -0.58
     brancas
    -0.57
    Jîn
    -0.54
    ℤ
    -0.53
     élevés
    -0.51
    írus
    -0.51
    DNEY
    -0.50
     extérieurs
    -0.50
    POSITIVE LOGITS
    numerusform
    0.67
    ScopeManager
    0.66
    IBarButtonItem
    0.63
     himself
    0.58
     herself
    0.56
    parseColor
    0.54
    jspx
    0.53
     CreateTagHelper
    0.52
    Skocz
    0.52
     NSCoder
    0.50
    Activations Density 2.092%

    No Known Activations