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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6828
    Prev
    Next
    INDEX
    Explanations

    words and phrases about holding positions in organizations along with dates

    oai_token-act-pair · gemini-2.0-flash

    held

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     myſelf
    -1.13
     ExecuteAsync
    -1.08
     itſelf
    -1.06
     Monfieur
    -1.04
     himſelf
    -0.97
     Theſe
    -0.95
     pleaſure
    -0.95
     themſelves
    -0.95
     iſt
    -0.94
     ſeveral
    -0.94
    POSITIVE LOGITS
    katy
    0.39
    tableFuture
    0.37
    ze
    0.36
    ne
    0.36
    pet
    0.36
     gracias
    0.35
    port
    0.35
    Reviewer
    0.35
    pc
    0.34
    <eos>
    0.34
    Activations Density 1.349%

    No Known Activations