© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11993
    Prev
    Next
    INDEX
    Explanations

    language discussing government finance, spending, laws, or regulations.

    oai_token-act-pair · gemini-2.0-flash

    Politics and economics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    esModule
    -0.64
     Waray
    -0.63
    adpleegd
    -0.57
    ellido
    -0.56
    DockStyle
    -0.54
     sapore
    -0.53
    Ligações
    -0.52
     שוליים
    -0.51
    KommentareTeilen
    -0.51
    vend
    -0.51
    POSITIVE LOGITS
    IUrlHelper
    0.51
     pleaſure
    0.47
     contextLoads
    0.46
     Majefty
    0.46
    [*]
    0.45
     Gaby
    0.45
     sej
    0.44
    madu
    0.42
    ubin
    0.42
    selves
    0.42
    Activations Density 5.270%

    No Known Activations