© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7327
    Prev
    Next
    INDEX
    Explanations

    places where text is disjointed, like around delimiters, newlines, or abrupt changes in content.

    oai_token-act-pair · gemini-2.0-flash

    sentence separator

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    idopsis
    -0.54
     StringTokenizer
    -0.53
    VertexAttrib
    -0.51
     שוליים
    -0.50
    出版年
    -0.49
    Identyfik
    -0.49
     الدولى
    -0.49
    CppMethod
    -0.49
    Rptr
    -0.48
    HasForeignKey
    -0.48
    POSITIVE LOGITS
     دیکھیے
    0.58
     for
    0.56
    For
    0.53
    ütfen
    0.52
    Ask
    0.51
     ویکی‌پدیا
    0.51
     For
    0.51
     Ask
    0.51
     nationaux
    0.50
     européennes
    0.50
    Activations Density 2.999%

    No Known Activations