© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13679
    Prev
    Next
    INDEX
    Explanations

    C++ related code, specifically class declarations/inheritance

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
    yntaxException
    -0.64
    vs
    -0.51
    成
    -0.49
     pings
    -0.49
     sessionFactory
    -0.48
    Демографія
    -0.48
    ModelSerializer
    -0.46
     vs
    -0.46
    ynb
    -0.45
     cristal
    -0.44
    POSITIVE LOGITS
     Jefus
    0.62
    webElementGuid
    0.62
     CreateTagHelper
    0.60
    ()]
    0.57
    ITERATURE
    0.57
    citenamefont
    0.57
    معلومات
    0.56
    textsc
    0.56
     ſmall
    0.55
     }}"></
    0.54
    Activations Density 0.173%

    No Known Activations