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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15725
    Prev
    Next
    INDEX
    Explanations

    filler words or punctuation marks commonly used in conversational writing or blogs.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    twimg
    -0.73
    
    -0.71
    новниш
    -0.63
    WebVitals
    -0.62
    ContentLoaded
    -0.62
     Bemer
    -0.61
     snippetHide
    -0.60
    expandindo
    -0.60
    ]")]
    -0.59
    原始内容存档于
    -0.59
    POSITIVE LOGITS
    Демографія
    0.56
     naturally
    0.51
    naturally
    0.48
    UnknownFieldSet
    0.47
    printLine
    0.47
     כן
    0.44
     naturellement
    0.44
    Bakgrunnsstoff
    0.43
     энциклопедия
    0.41
     chestnuts
    0.41
    Activations Density 2.700%

    No Known Activations