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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1163
    Prev
    Next
    INDEX
    Explanations

    tokens related to culture and cultural erosion, plus the word "bring"

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     Majefty
    -1.07
     purpoſe
    -1.05
     Theſe
    -1.03
     myſelf
    -0.98
     itſelf
    -0.96
     Efq
    -0.95
     Jefus
    -0.93
     Chriftian
    -0.93
     Houſe
    -0.92
     Monfieur
    -0.91
    POSITIVE LOGITS
    <bos>
    0.46
    AutoSize
    0.46
    loc
    0.43
     comp
    0.43
    el
    0.42
    fit
    0.41
    J
    0.40
    setVerticalGroup
    0.39
     fit
    0.39
    ,
    0.39
    Activations Density 1.413%

    No Known Activations