© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    mentions of "edit" in the context of code or web pages

    oai_token-act-pair · gemini-2.0-flash

    edit

    np_max-act · gemini-2.0-flash
    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
    OGND
    -0.77
    zzleHttp
    -0.65
    bootstrapcdn
    -0.62
     Ouverture
    -0.56
    hoga
    -0.55
     partai
    -0.54
     letteratura
    -0.54
    alisasi
    -0.53
     vœux
    -0.52
     استنادى
    -0.51
    POSITIVE LOGITS
    EndInit
    0.56
    LayoutInflater
    0.50
     <<<<<<<<<<<<<<
    0.49
    AsUp
    0.48
    ResumeLayout
    0.47
    ActivityResult
    0.45
     arşivlendi
    0.44
    BeginInit
    0.44
    featureID
    0.44
    }}]{
    0.43
    Activations Density 2.527%

    No Known Activations