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. 7129
    Prev
    Next
    INDEX
    Explanations

    the word "suitable"

    oai_token-act-pair · gemini-2.0-flash

    suitable

    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
    Архівовано
    -1.08
     Efq
    -1.05
    存于互联网档案馆
    -0.99
     myſelf
    -0.93
    extAlignment
    -0.92
    ^(@)
    -0.91
     Houſe
    -0.91
    ſelf
    -0.91
     Majefty
    -0.90
     Theſe
    -0.90
    POSITIVE LOGITS
    -
    0.63
    ↵↵
    0.62
    (
    0.61
    .
    0.55
    ).
    0.53
    _
    0.52
    <eos>
    0.52
     (
    0.51
    ..
    0.50
    –
    0.49
    Activations Density 0.634%

    No Known Activations