© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1272
    Prev
    Next
    INDEX
    Explanations

    code or code-like syntax, particularly related to website analytics and network communication

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Biôgrafia
    -0.71
    StreetMap
    -0.69
    клопе
    -0.63
    elemField
    -0.60
    ViewFeatures
    -0.59
    ροφο
    -0.59
    <bos>
    -0.59
    ondy
    -0.55
    mbic
    -0.52
    rony
    -0.51
    POSITIVE LOGITS
    DebuggerStep
    0.59
     XCTest
    0.46
    ynen
    0.45
    ')['
    0.44
     "..\..\..\
    0.44
    ENR
    0.43
     AssemblyCompany
    0.43
    envs
    0.43
     فريبيس
    0.43
     betweenstory
    0.42
    Activations Density 1.273%

    No Known Activations