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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8074
    Prev
    Next
    INDEX
    Explanations

    the letter "g" after a vowel, often in scientific texts

    oai_token-act-pair · gemini-2.0-flash

    g

    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
     g
    -1.08
     G
    -1.07
    g
    -1.02
    te
    -0.73
    e
    -0.69
    G
    -0.66
    i
    -0.63
     K
    -0.63
    ++;
    -0.59
    <eos>
    -0.59
    POSITIVE LOGITS
     resourceCulture
    1.20
    +#+#
    1.07
     ſever
    0.89
     itſelf
    0.87
     themſelves
    0.87
     raiſ
    0.87
     Houſe
    0.86
     Shakspeare
    0.86
     GetEnumerator
    0.86
     Reſ
    0.83
    Activations Density 1.962%

    No Known Activations