© 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. 14510
    Prev
    Next
    INDEX
    Explanations

    java code that consists of an if/else if block

    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
     AssemblyTitle
    -0.65
     esternos
    -0.46
     aidant
    -0.43
     parlé
    -0.42
    amię
    -0.42
    లాలు
    -0.41
     ég
    -0.41
     déclaré
    -0.40
     polaire
    -0.40
    商品説明
    -0.39
    POSITIVE LOGITS
    glGen
    0.69
    newBuilder
    0.66
    -
    0.63
    sockfd
    0.61
    tableView
    0.61
    tencent
    0.60
     jButton
    0.60
    BeforeClass
    0.60
    rals
    0.59
     >::
    0.58
    Activations Density 17.676%

    No Known Activations