© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8952
    Prev
    Next
    INDEX
    Explanations

    acronyms or technical abbreviations

    oai_token-act-pair · gemini-2.0-flash

    meter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.06
    Спољашње
    -0.94
    BeginContext
    -0.70
     nahilalakip
    -0.69
    Datuak
    -0.69
    Tikang
    -0.66
    /**
    -0.66
     Paglinawan
    -0.63
    SourceChecksum
    -0.61
    endpush
    -0.58
    POSITIVE LOGITS
    makeConstraints
    0.54
     orgánico
    0.51
     Curs
    0.50
     scorso
    0.50
    viewDidLoad
    0.48
    databind
    0.47
     ely
    0.47
    traje
    0.47
    fastjson
    0.46
    scalatest
    0.46
    Activations Density 3.237%

    No Known Activations