© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10196
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    ampersand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    '].'
    -0.55
    medad
    -0.55
    |$.
    -0.53
     assim
    -0.51
    ionalmente
    -0.51
     GIPHY
    -0.50
    asd
    -0.48
    ródła
    -0.48
    ipel
    -0.48
    WAUKEE
    -0.48
    POSITIVE LOGITS
     &
    1.82
    &
    1.52
    .&
    1.20
    ,&
    1.12
     \&
    1.08
    &\
    1.05
     &\
    1.03
     &.
    1.02
    (&
    1.02
     '&
    1.02
    Activations Density 2.191%

    No Known Activations