© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14301
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those related to web development, APIs, and possibly specific libraries or languages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     invokingState
    -0.65
    ExtendWith
    -0.65
    ()?
    -0.61
    "।
    -0.59
    "?
    -0.59
     Philist
    -0.58
    phosa
    -0.57
    ISupport
    -0.57
    ?";
    -0.57
    '?
    -0.56
    POSITIVE LOGITS
    ↵
    0.67
    DataAnnotations
    0.54
    tipped
    0.52
    CÁ
    0.51
    ↵↵
    0.48
    empêcher
    0.46
     AssemblyCulture
    0.46
    hending
    0.46
     découver
    0.46
    antMatchers
    0.46
    Activations Density 4.804%

    No Known Activations