© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6667
    Prev
    Next
    INDEX
    Explanations

    code-like structures

    oai_token-act-pair · gemini-2.0-flash

    code-related text

    np_max-act-logits · gemini-2.0-flash

    say "Capitalized words"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     respective
    -0.21
    !("{}",
    -0.18
     non
    -0.18
     longterm
    -0.18
     second
    -0.17
     ones
    -0.17
     third
    -0.17
     high
    -0.17
     newly
    -0.17
     unique
    -0.16
    POSITIVE LOGITS
     démocr
    0.56
     quelcon
    0.56
    Parking
    0.56
    Train
    0.54
    Weather
    0.52
    Cover
    0.52
    Traffic
    0.52
    Battery
    0.52
    Gender
    0.52
    History
    0.52
    Activations Density 70.087%

    No Known Activations