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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14223
    Prev
    Next
    INDEX
    Explanations

    random strings of capital letters and numbers, often found in URLs

    oai_token-act-pair · gemini-2.0-flash

    web or youtube links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    parsedMessage
    -1.01
     myſelf
    -0.93
     ſtate
    -0.91
     Jefus
    -0.91
    IntoConstraints
    -0.91
     himſelf
    -0.90
     ſeveral
    -0.88
     houſe
    -0.85
     themſelves
    -0.84
     Majefty
    -0.83
    POSITIVE LOGITS
    te
    0.42
    frameCount
    0.39
    SD
    0.39
     C
    0.38
    ingar
    0.37
    TE
    0.36
    Per
    0.36
    MA
    0.35
    warma
    0.35
    DU
    0.34
    Activations Density 1.227%

    No Known Activations