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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14494
    Prev
    Next
    INDEX
    Explanations

    the words "break", "continue", "tag", "bio", "end", "receive", or "quiz" in blocks of code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     EconPapers
    -0.79
     Zacks
    -0.64
    StoryboardSegue
    -0.63
    Hozzáférés
    -0.63
     Vikipedi
    -0.60
    первых
    -0.60
     onCancelled
    -0.59
    NavController
    -0.56
    forth
    -0.56
     فريبيس
    -0.55
    POSITIVE LOGITS
    <bos>
    1.49
    '
    0.71
     itſelf
    0.57
     Monfieur
    0.57
     nahilalakip
    0.54
    ↵↵
    0.54
     myſelf
    0.54
    unmodifiable
    0.53
    posób
    0.52
    SourceChecksum
    0.51
    Activations Density 1.504%

    No Known Activations