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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3711
    Prev
    Next
    INDEX
    Explanations

    a wide variety of things including comments in code, copyright notices, names of months, colons, and the word series

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     porém
    -0.52
     this
    -0.50
     these
    -0.49
    .*")]
    -0.48
     therefore
    -0.48
    ")));
    
    -0.47
    hereinafter
    -0.47
     portanto
    -0.47
     although
    -0.46
    ()][
    -0.45
    POSITIVE LOGITS
    head
    0.88
    track
    0.86
    top
    0.86
    key
    0.86
    code
    0.85
    path
    0.84
    view
    0.82
    line
    0.82
    bar
    0.82
    field
    0.82
    Activations Density 10.040%

    No Known Activations