© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10802
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical or scientific procedures and models

    oai_token-act-pair · gemini-2.0-flash

    Method/Procedure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tagHelperRunner
    -0.72
    :✨
    -0.60
     defaultstate
    -0.51
    Referencias
    -0.50
     <=",
    -0.48
    rema
    -0.47
    ;->
    -0.47
    See
    -0.47
    Personendaten
    -0.46
    GenerationType
    -0.46
    POSITIVE LOGITS
     tả
    0.66
     described
    0.64
     décrit
    0.56
    Descricao
    0.55
     Macromolecules
    0.54
     LUMP
    0.54
    ItemBackground
    0.54
     Descriptions
    0.53
     Texts
    0.52
    描述
    0.52
    Activations Density 3.692%

    No Known Activations