© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10537
    Prev
    Next
    INDEX
    Explanations

    uses of the word "a" or "the" related to studies and ambitious goals.

    oai_token-act-pair · gemini-2.0-flash

    new

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ReadInt
    -0.43
    로그램
    -0.43
    bukkit
    -0.42
    ixeira
    -0.42
    randn
    -0.39
    antMatchers
    -0.38
    laires
    -0.38
    сут
    -0.38
    REY
    -0.37
     apporter
    -0.37
    POSITIVE LOGITS
     new
    2.86
    new
    2.42
     nieuwe
    1.96
     neuen
    1.91
     neue
    1.91
     nueva
    1.91
     nuevos
    1.89
     nuevas
    1.84
     nuovo
    1.79
     nuova
    1.79
    Activations Density 1.234%

    No Known Activations