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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16172
    Prev
    Next
    INDEX
    Explanations

    mathematical and legal symbols or abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Mathematical equations and nitrogen labels. (This is the best guess)

    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
     n
    -1.30
    n
    -1.25
    ｎ
    -0.98
    nn
    -0.91
    nnnn
    -0.85
    nnn
    -0.80
     nn
    -0.79
    ns
    -0.79
    𝑛
    -0.76
    nc
    -0.74
    POSITIVE LOGITS
     Ν
    0.66
     Ն
    0.65
    𝑁
    0.56
     На
    0.56
     Nu
    0.54
     Nig
    0.52
     Ne
    0.51
    Nl
    0.50
     ویکی‌پدی
    0.47
     betweenstory
    0.47
    Activations Density 3.161%

    No Known Activations