© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14358
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to research, opinion, argumentation, or formal demonstration

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ſmall
    -0.75
     ſt
    -0.72
     onCreateView
    -0.71
     Bigelow
    -0.67
    RemoveField
    -0.66
     itſelf
    -0.65
     ſche
    -0.63
     myſelf
    -0.63
    ſelves
    -0.63
     ſever
    -0.63
    POSITIVE LOGITS
    Искәрмәләр
    0.70
    MENAFN
    0.61
    fjspx
    0.54
     flé
    0.48
     led
    0.46
     working
    0.44
    WriteTagHelper
    0.43
    agisse
    0.42
     jspb
    0.42
     кӀ
    0.42
    Activations Density 16.469%

    No Known Activations