Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13458
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly those involving matrix or array operations, indexing, and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    colon or comma

    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
    +:+
    -0.56
    nahme
    -0.50
    ValueGenerated
    -0.48
     tratta
    -0.46
    helfen
    -0.45
     estiver
    -0.45
     nalazi
    -0.44
    ёв
    -0.44
     startY
    -0.43
     quiser
    -0.43
    POSITIVE LOGITS
    RectangleBorder
    0.88
     kasarigan
    0.77
     nahilalakip
    0.74
    IBOutlet
    0.67
    PerformLayout
    0.66
    tagHelperRunner
    0.66
    ourage
    0.65
    WithIOException
    0.63
    AccessorTable
    0.61
    Portály
    0.60
    Activations Density 17.153%

    No Known Activations