© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6631
    Prev
    Next
    INDEX
    Explanations

    the word "once" sometimes in conjunction with other words

    oai_token-act-pair · gemini-2.0-flash

    once

    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
     once
    -0.95
    once
    -0.73
     ONCE
    -0.68
    ONCE
    -0.65
     Once
    -0.64
    Once
    -0.63
     newBuilder
    -0.63
     inex
    -0.61
    roch
    -0.61
    resizingMask
    -0.60
    POSITIVE LOGITS
     étoient
    0.68
     picioare
    0.67
     avoient
    0.64
     mariée
    0.63
     rencont
    0.63
     blessés
    0.62
     occupé
    0.61
     pymysql
    0.61
     généraux
    0.61
     journalistes
    0.61
    Activations Density 0.868%

    No Known Activations