© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9798
    Prev
    Next
    INDEX
    Explanations

    mentions of source code repositories and related actions like linking

    oai_token-act-pair · gemini-2.0-flash

    Pointers and references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AssemblyCulture
    -1.07
     ModelExpression
    -0.84
     EconPapers
    -0.82
     kasarigan
    -0.81
    RenderAtEndOf
    -0.77
    __.__
    -0.75
    SourceChecksum
    -0.74
     chi̍t
    -0.73
    OrBuilder
    -0.73
     CURIAM
    -0.73
    POSITIVE LOGITS
     kepada
    0.79
     đến
    0.69
     به
    0.65
     onto
    0.64
     unto
    0.63
     to
    0.62
     terhadap
    0.61
     tới
    0.60
    ถึง
    0.59
     siihen
    0.57
    Activations Density 1.232%

    No Known Activations