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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6562
    Prev
    Next
    INDEX
    Explanations

    uses of the word "yet" along with the surrounding words

    oai_token-act-pair · gemini-2.0-flash

    yet

    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
    -------
    -0.85
     cherchés
    -0.84
     Económica
    -0.83
    NUMX
    -0.77
    <bos>
    -0.75
     становника
    -0.75
    ThroughAttribute
    -0.73
     labors
    -0.71
    ſelf
    -0.70
    __":
    -0.68
    POSITIVE LOGITS
     Alternatively
    0.69
    Alternatively
    0.63
     utilis
    0.61
    Whilst
    0.61
     Whilst
    0.60
     enquiries
    0.57
     násled
    0.54
     venne
    0.53
    hichever
    0.52
     eventual
    0.50
    Activations Density 1.954%

    No Known Activations