© 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. 212
    Prev
    Next
    INDEX
    Explanations

    company names

    oai_token-act-pair · gemini-2.0-flash

    code related

    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
    ukone
    -0.59
     autorytatywna
    -0.57
    IndentedString
    -0.56
     AssemblyTitle
    -0.51
    brück
    -0.51
     lifted
    -0.51
     Мексичка
    -0.50
    sedown
    -0.49
    ichord
    -0.48
     transfieras
    -0.47
    POSITIVE LOGITS
    mockito
    0.59
     BrowserModule
    0.55
    XmlType
    0.54
     ESG
    0.53
    ValueGenerated
    0.52
     setuptools
    0.52
    RegressionTest
    0.52
     SVN
    0.52
    BrowserModule
    0.51
     XCTest
    0.51
    Activations Density 6.729%

    No Known Activations