© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4451
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations, especially in scientific or technical contexts

    oai_token-act-pair · gemini-2.0-flash

    all-caps abbreviations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     فريبيس
    -0.73
    ImageContext
    -0.71
    ScopeManager
    -0.67
    ništ
    -0.61
    abancı
    -0.60
    ConverterFactory
    -0.57
    OpenHelper
    -0.56
     nahilalakip
    -0.54
    zzleHttp
    -0.54
    SuppressLint
    -0.54
    POSITIVE LOGITS
    𝟹
    0.57
    __":
    0.53
    SharedCtor
    0.52
     Conſ
    0.51
     poveznice
    0.50
    choenen
    0.49
     Lég
    0.48
    värr
    0.48
     igång
    0.48
     réguli
    0.48
    Activations Density 0.828%

    No Known Activations