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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7317
    Prev
    Next
    INDEX
    Explanations

    words related to institutions and management

    oai_token-act-pair · gemini-2.0-flash

    plan and management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.65
    <bos>
    -0.64
    <eos>
    -0.62
    ↵
    -0.54
    -
    -0.52
     I
    -0.50
     “
    -0.49
     (
    -0.48
     The
    -0.48
    Todavía
    -0.47
    POSITIVE LOGITS
     Monfieur
    1.20
     Efq
    1.19
     Shakspeare
    1.15
     greateſt
    1.11
     houſe
    1.09
     Theſe
    1.09
     themſelves
    1.08
     myſelf
    1.07
     ſeveral
    1.07
     ſtate
    1.07
    Activations Density 0.634%

    No Known Activations