© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8007
    Prev
    Next
    INDEX
    Explanations

    seemingly random formatting characters in code or text

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     if
    -3.11
    if
    -2.70
     если
    -1.98
     jika
    -1.91
     dacă
    -1.87
     nếu
    -1.79
     якщо
    -1.73
    If
    -1.53
     wenn
    -1.52
    если
    -1.52
    POSITIVE LOGITS
    __':
    0.83
     mergeFrom
    0.75
    __":
    0.72
     propOrder
    0.65
     AssemblyTitle
    0.62
    __(/*!
    0.61
    ंदीखरीदारी
    0.59
    parsedMessage
    0.57
    __':
    0.57
     ExecuteAsync
    0.55
    Activations Density 2.833%

    No Known Activations