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. 14226
    Prev
    Next
    INDEX
    Explanations

    words expressing ability or possibility

    oai_token-act-pair · 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
     neust
    -0.36
     segn
    -0.35
    chenta
    -0.35
    maker
    -0.35
     cu
    -0.35
    الش
    -0.34
    zyw
    -0.34
     Uniform
    -0.34
     Forward
    -0.33
     Mä
    -0.33
    POSITIVE LOGITS
     MessageBoxIcon
    0.88
     AssemblyTitle
    0.81
    StoryboardSegue
    0.79
    rungsseite
    0.77
     становника
    0.75
    +#+
    0.74
    moiselle
    0.73
    InstrumentedTest
    0.72
     LoginComponent
    0.71
     Crusoe
    0.70
    Activations Density 0.788%

    No Known Activations