© 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. 13860
    Prev
    Next
    INDEX
    Explanations

    lines of code involving variable assignment, especially with equals signs and bracketed array access

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    <eos>
    -0.65
    .
    -0.57
    ,
    -0.53
    –
    -0.47
    la
    -0.47
    ho
    -0.47
    (
    -0.46
    uc
    -0.45
    ↵
    -0.45
    ¿
    -0.45
    POSITIVE LOGITS
     myſelf
    1.34
     Efq
    1.27
    ^(@)
    1.23
     houſe
    1.21
     Jefus
    1.18
    AddTagHelper
    1.17
    ſelf
    1.15
    BibitemShut
    1.15
     resourceCulture
    1.13
     ſmall
    1.13
    Activations Density 9.755%

    No Known Activations