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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13502
    Prev
    Next
    INDEX
    Explanations

    verbs, particularly those ending in "s."

    oai_token-act-pair · gemini-2.0-flash

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.05
    '
    -0.63
    ’
    -0.60
    -
    -0.57
    (
    -0.52
     bet
    -0.50
    n
    -0.49
    te
    -0.46
    ,
    -0.46
    “
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.78
    pertino
    0.77
     HasFactory
    0.76
     Majefty
    0.74
     Houſe
    0.69
    tesy
    0.69
    Попис
    0.67
    !("{}",
    0.66
     Miscell
    0.66
     firebaseConfig
    0.65
    Activations Density 6.728%

    No Known Activations