© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    code or pseudocode related to graphs and adjacency lists

    oai_token-act-pair · gemini-2.0-flash

    jac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    imageshack
    -0.68
     Crosse
    -0.66
    脚注の使い方
    -0.65
     '\\;'
    -0.60
    setof
    -0.59
    argout
    -0.59
    SourceChecksum
    -0.57
     محفوظة
    -0.57
    offsetof
    -0.57
    EventLoop
    -0.56
    POSITIVE LOGITS
     neighbor
    1.27
     neighbors
    1.24
     neighboring
    1.19
     neighbour
    1.16
     Neighbor
    1.14
     neighbours
    1.13
    neighbor
    1.12
     Neighbors
    1.12
     neighbouring
    1.09
    Neighbor
    1.09
    Activations Density 0.856%

    No Known Activations