© 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. 1033
    Prev
    Next
    INDEX
    Explanations

    a mix of mathematical formulas, French words, and technical internet terms

    oai_token-act-pair · gemini-2.0-flash

    n

    np_max-act-logits · 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
     neither
    -1.92
     none
    -1.72
    neither
    -1.66
     nobody
    -1.62
     Neither
    -1.52
    Neither
    -1.47
     nothing
    -1.43
     nowhere
    -1.38
     never
    -1.38
     não
    -1.36
    POSITIVE LOGITS
     n
    0.98
    N
    0.88
     N
    0.86
    n
    0.83
    ｎ
    0.69
    getN
    0.67
    nC
    0.66
    𝑛
    0.60
    𝗻
    0.59
    𝙣
    0.59
    Activations Density 4.886%

    No Known Activations