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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6961
    Prev
    Next
    INDEX
    Explanations

    references to companies, groups of people, or the word "I"

    oai_token-act-pair · gemini-2.0-flash

    Business and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     try
    -0.59
     trying
    -0.59
     tries
    -0.57
     works
    -0.55
     prepare
    -0.55
     wait
    -0.54
     TRY
    -0.54
     build
    -0.52
     recuper
    -0.51
    adjust
    -0.50
    POSITIVE LOGITS
    saraba
    0.72
     تانيه
    0.71
    InjectAttribute
    0.70
    OGND
    0.69
    providedIn
    0.68
     linkovi
    0.68
     AppCompatTheme
    0.68
     שוליים
    0.67
    UserScript
    0.67
    beiros
    0.66
    Activations Density 1.346%

    No Known Activations