© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9913
    Prev
    Next
    INDEX
    Explanations

    uses of the phrase "by the way" and "by far."

    oai_token-act-pair · gemini-2.0-flash

    way far

    np_max-act · gemini-2.0-flash

    by (as in "by the"/"by far")

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     disponibilités
    -0.82
    yntaxException
    -0.70
    sizeCache
    -0.62
    Personendaten
    -0.61
    INCREF
    -0.60
    évaluateur
    -0.60
    IntoConstraints
    -0.59
    ActionCreators
    -0.59
     '\\;'
    -0.58
    IsMutable
    -0.57
    POSITIVE LOGITS
    raszam
    0.56
    )");
    0.56
    ництво
    0.55
     voti
    0.55
     '/')
    0.53
    тельство
    0.53
     امريكا
    0.52
    )=>{
    0.51
    --)
    0.51
    chede
    0.51
    Activations Density 1.400%

    No Known Activations