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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16147
    Prev
    Next
    INDEX
    Explanations

    Objective-C code, specifically class declarations and method definitions

    oai_token-act-pair · gemini-2.0-flash

    Code/Programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    underscore
    -0.56
     par
    -0.52
    WidgetItem
    -0.52
    NullException
    -0.51
     by
    -0.50
    forRoot
    -0.50
    lates
    -0.45
     euch
    -0.45
     por
    -0.44
     pelo
    -0.43
    POSITIVE LOGITS
     VIAF
    0.75
    ########.
    0.69
    AsUp
    0.69
     itſelf
    0.68
     ſtand
    0.68
    ьаж
    0.67
     zelve
    0.67
     pleaſure
    0.66
    OGND
    0.66
     leſs
    0.65
    Activations Density 0.927%

    No Known Activations