© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12649
    Prev
    Next
    INDEX
    Explanations

    the word "often" and words that are adjacent to it

    oai_token-act-pair · gemini-2.0-flash

    often

    np_max-act · gemini-2.0-flash
    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
     often
    -2.59
    often
    -2.20
     Often
    -2.08
    Often
    -2.05
     spesso
    -1.96
     souvent
    -1.91
     sometimes
    -1.83
     oftentimes
    -1.70
     často
    -1.70
     frequently
    -1.70
    POSITIVE LOGITS
     متعلقه
    0.67
     թվական
    0.61
    outheast
    0.57
    цездатний
    0.57
    IntoConstraints
    0.55
    expandindo
    0.54
     menthe
    0.54
    tawesome
    0.53
     مُعرِّف
    0.53
     Möglich
    0.52
    Activations Density 1.028%

    No Known Activations