© 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. 13093
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_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
     zelve
    -0.60
     noastre
    -0.60
     purpoſe
    -0.59
     houſe
    -0.57
     noastră
    -0.57
     marquées
    -0.57
     eorum
    -0.56
     acoper
    -0.56
    OrNil
    -0.56
    thane
    -0.56
    POSITIVE LOGITS
     AssemblyCulture
    0.83
    invokeLater
    0.65
    AnimationsModule
    0.64
     BoxDecoration
    0.62
    ViewImports
    0.58
    atigable
    0.56
    IRECT
    0.53
    AutoScaleMode
    0.52
    addLast
    0.50
     Bele
    0.50
    Activations Density 0.360%

    No Known Activations