© 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. 4443
    Prev
    Next
    INDEX
    Explanations

    code snippets and related keywords such as "client" and "response" within a software context possibly related to networking or data transfer.

    oai_token-act-pair · gemini-2.0-flash

    say "List"

    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
    gorm
    -0.58
    richTextPanel
    -0.56
     linkovi
    -0.54
    estacks
    -0.52
     kort
    -0.49
    numerusform
    -0.48
    radio
    -0.45
     stile
    -0.45
     bart
    -0.45
     JADX
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.68
    verständlich
    0.64
    ocimiento
    0.60
     itſelf
    0.60
     ModelExpression
    0.59
    Kemudian
    0.59
    aporan
    0.57
    ècie
    0.57
     vậy
    0.56
     تانيه
    0.56
    Activations Density 1.360%

    No Known Activations