© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15952
    Prev
    Next
    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    int

    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
     useAppContext
    -0.58
    bootstrapcdn
    -0.52
    DeleteMapping
    -0.52
     exemplaires
    -0.50
    ^(@)
    -0.48
     Corée
    -0.48
     guère
    -0.48
    Versch
    -0.47
     mérit
    -0.46
    "):
    -0.46
    POSITIVE LOGITS
    Зноскі
    0.57
    ReusableCell
    0.57
     autorytatywna
    0.56
     EconPapers
    0.55
    ttino
    0.54
    DebuggerNonUser
    0.52
     Fil
    0.52
     <<<<<<<<<<<<<<
    0.51
    iotensin
    0.50
     linkovi
    0.49
    Activations Density 1.101%

    No Known Activations