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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6961
    Prev
    Next
    INDEX
    Explanations

    job titles and company names

    oai_token-act-pair · gemini-2.0-flash

    senior, deputy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    szönöm
    -0.60
    ModelForm
    -0.52
    ableness
    -0.52
    bgp
    -0.51
    chaun
    -0.51
    fcntl
    -0.50
    się
    -0.49
     subd
    -0.48
    popd
    -0.48
    новниш
    -0.47
    POSITIVE LOGITS
    EDEFAULT
    0.61
    ValueGenerated
    0.57
    RegistryLite
    0.52
    FXML
    0.52
    Suggested
    0.50
     Ее
    0.50
    ']")
    0.49
     Его
    0.49
    }")
    
    0.48
    Gön
    0.48
    Activations Density 6.695%

    No Known Activations