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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12017
    Prev
    Next
    INDEX
    Explanations

    code-related entities such as variable names, types and functions

    oai_token-act-pair · gemini-2.0-flash

    special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ^(@)
    -1.73
     Efq
    -1.71
     myſelf
    -1.70
     Theſe
    -1.66
     Jefus
    -1.65
    ſelf
    -1.65
     Monfieur
    -1.63
    ſelves
    -1.62
     betweenstory
    -1.56
     itſelf
    -1.54
    POSITIVE LOGITS
    ↵↵
    0.68
    2
    0.50
    ,
    0.48
    <eos>
    0.48
    .
    0.47
    <strong>
    0.45
    1
    0.44
    ↵
    0.43
    4
    0.42
    5
    0.41
    Activations Density 8.430%

    No Known Activations