© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    file paths, directories and environment variable assignments, possibly related to nginx

    oai_token-act-pair · gemini-2.0-flash

    File paths/code

    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
     directory
    -1.33
     folder
    -1.23
     Directory
    -1.20
     directories
    -1.18
     Folder
    -1.16
    Directory
    -1.16
     folders
    -1.15
     dir
    -1.07
    directory
    -1.06
    Dir
    -1.03
    POSITIVE LOGITS
     банка
    0.44
     beru
    0.43
    Banks
    0.42
    LEncoder
    0.42
     fiquei
    0.41
     באתר
    0.40
     mit
    0.40
     obce
    0.38
     Energie
    0.38
     kommunen
    0.38
    Activations Density 0.717%

    No Known Activations