© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14109
    Prev
    Next
    INDEX
    Explanations

    words related to programming, or question asking related to "someone/anyone". It also finds the word "volunteers."

    oai_token-act-pair · gemini-2.0-flash

    programming or volunteering or French

    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
     تضيفلها
    -0.87
     BrowserModule
    -0.69
    ngdoc
    -0.66
     للمعارف
    -0.61
    ContentAsync
    -0.60
    WebElementEntity
    -0.59
     defaultstate
    -0.59
    setVerticalGroup
    -0.59
    帖最后由
    -0.59
     للاسماء
    -0.58
    POSITIVE LOGITS
    IntoConstraints
    0.62
    πάρχ
    0.60
    ();)
    0.51
     Lleva
    0.48
    MLLoader
    0.48
    PasswordEncoder
    0.47
    mappedBy
    0.45
    Autowired
    0.44
    posedge
    0.44
     насељу
    0.44
    Activations Density 3.654%

    No Known Activations