© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5722
    Prev
    Next
    INDEX
    Explanations

    questions asking for help or explanation

    oai_token-act-pair · gemini-2.0-flash

    requesting information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    setVerticalGroup
    -0.66
     незавершена
    -0.57
     Мексичка
    -0.54
    findpost
    -0.53
     EconPapers
    -0.52
     సౌకర్య
    -0.52
     transfieras
    -0.51
    UnsafeEnabled
    -0.51
     study
    -0.50
    MarshalTo
    -0.49
    POSITIVE LOGITS
     tell
    1.08
    Tell
    1.04
     Tell
    1.03
     TELL
    1.02
    TELL
    0.88
     explain
    0.87
     Explain
    0.87
     please
    0.86
     inform
    0.83
    Explain
    0.80
    Activations Density 1.793%

    No Known Activations