© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3427
    Prev
    Next
    INDEX
    Explanations

    parts of academic papers, like formal names, locations, and funding sources

    oai_token-act-pair · gemini-2.0-flash

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AndEndTag
    -0.79
     vastaan
    -0.71
    InputBorder
    -0.70
    StructEnd
    -0.66
     abstrait
    -0.65
     tantôt
    -0.63
     étrangère
    -0.62
     ogrodow
    -0.62
     Antara
    -0.62
    mbic
    -0.61
    POSITIVE LOGITS
    izeit
    0.54
     Pare
    0.51
     ").
    0.50
    ")));
    0.49
     Par
    0.48
    zarchiwizowane
    0.47
     كومونز
    0.46
     Ю
    0.46
     sti
    0.45
    IBOutlet
    0.45
    Activations Density 1.458%

    No Known Activations