© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8114
    Prev
    Next
    INDEX
    Explanations

    commas and periods, especially when near certain conjunctions like "and" or "thus"

    oai_token-act-pair · gemini-2.0-flash

    commas

    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
     Theſe
    -1.41
     Efq
    -1.35
     myſelf
    -1.32
     themſelves
    -1.30
     Monfieur
    -1.29
     Houſe
    -1.27
     Reſ
    -1.23
     houſe
    -1.23
     Anſ
    -1.22
     Diſ
    -1.21
    POSITIVE LOGITS
    <bos>
    1.50
    <eos>
    0.85
    '
    0.80
    ↵↵
    0.77
     
    0.65
     I
    0.64
    ’
    0.63
     the
    0.57
     '
    0.57
     c
    0.56
    Activations Density 1.114%

    No Known Activations