© 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. 10601
    Prev
    Next
    INDEX
    Explanations

    forum-like text, including greetings, questions and answers, and formatting related to programming

    oai_token-act-pair · gemini-2.0-flash

    code help forum

    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
     ErrIntOverflow
    -0.69
    NameInMap
    -0.67
    enumi
    -0.65
    UnusedPrivate
    -0.62
    WithIOException
    -0.60
    XMLSchema
    -0.59
    ButterKnife
    -0.59
    brigens
    -0.59
     AssemblyCulture
    -0.59
    contentLoaded
    -0.58
    POSITIVE LOGITS
    
    0.47
    }{*}{
    0.47
    vokat
    0.47
    AnchorStyles
    0.46
     snippetHide
    0.46
     Mam
    0.45
    ⇄
    0.45
    %:
    0.43
    />";
    0.43
     mam
    0.42
    Activations Density 3.175%

    No Known Activations