© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5904
    Prev
    Next
    INDEX
    Explanations

    instances of can, will, would, could, going to, may, that, all, tend to, products, that, happen to, able, segment, green.

    oai_token-act-pair · gemini-2.0-flash

    Diverse topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ChildScrollView
    -0.79
    LookAnd
    -0.71
    NewUrlParser
    -0.69
    NameInMap
    -0.66
     initComponents
    -0.65
    RegressionTest
    -0.64
    webElementXpaths
    -0.60
    BeginInit
    -0.59
    yarnpkg
    -0.59
    resave
    -0.56
    POSITIVE LOGITS
    Билгалдахарш
    0.48
     pistons
    0.47
     visas
    0.45
    riebe
    0.44
     onResponse
    0.44
     bikes
    0.43
     water
    0.43
    ircraft
    0.42
     intelligen
    0.41
     Thunderbolt
    0.40
    Activations Density 7.632%

    No Known Activations