Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6970
    Prev
    Next
    INDEX
    Explanations

    the words "rule" or "rules" or "Rule" or "rules"

    oai_token-act-pair · gemini-2.0-flash

    rules

    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
     trekken
    -0.64
    حياته
    -0.63
    elsa
    -0.59
    epiece
    -0.57
     CreateTagHelper
    -0.57
    +#+
    -0.56
     sava
    -0.55
     resourceCulture
    -0.55
    WriteLiteral
    -0.54
    DoubleQuotes
    -0.52
    POSITIVE LOGITS
    <bos>
    1.44
     myſelf
    1.16
     itſelf
    1.10
     pleaſure
    1.02
     Monfieur
    1.01
     ſmall
    0.96
     ſeveral
    0.95
     reaſon
    0.94
     purpoſe
    0.93
    ſelf
    0.93
    Activations Density 0.576%

    No Known Activations