© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 323
    Prev
    Next
    INDEX
    Explanations

    code snippets from Microsoft and other tech companies, as well as Jewish religious passages.

    oai_token-act-pair · gemini-2.0-flash

    Source code and Bible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     alike
    -0.59
    期刊论文
    -0.54
    HasBeenSet
    -0.52
    SharedCtor
    -0.51
     geldig
    -0.51
    AddAttribute
    -0.50
     (;;
    -0.47
     galería
    -0.46
    jskiej
    -0.46
     CreateTagHelper
    -0.46
    POSITIVE LOGITS
    ########.
    0.63
    irchen
    0.59
    HasForeignKey
    0.57
    umán
    0.57
    straints
    0.53
     springfox
    0.52
    andExpect
    0.52
     skład
    0.52
    webElementXpaths
    0.51
    وفاته
    0.51
    Activations Density 2.413%

    No Known Activations