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. 7182
    Prev
    Next
    INDEX
    Explanations

    the word "to"

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    <bos>
    -1.80
    Personensuche
    -1.08
     nahilalakip
    -1.07
    UnusedPrivate
    -1.05
    AsUp
    -1.05
     '\\;'
    -1.05
    LookAnd
    -1.02
     AssemblyCulture
    -1.02
    цездатний
    -1.02
    uxxxx
    -1.00
    POSITIVE LOGITS
     more
    0.69
     it
    0.69
     some
    0.69
     many
    0.67
     various
    0.67
     a
    0.66
     as
    0.66
     most
    0.65
     if
    0.65
     the
    0.65
    Activations Density 1.287%

    No Known Activations