© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11324
    Prev
    Next
    INDEX
    Explanations

    words related to exiting, radioactivity, code, and the French language.

    oai_token-act-pair · gemini-2.0-flash

    Exiting

    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
     Roskov
    -0.67
     فريبيس
    -0.54
    ثيق
    -0.53
    anka
    -0.52
    ForRow
    -0.51
    rostis
    -0.51
    tionnaire
    -0.50
    roves
    -0.49
     TMPro
    -0.48
     aidant
    -0.47
    POSITIVE LOGITS
    getOut
    0.98
    Out
    0.91
     Exit
    0.90
     Out
    0.89
     exit
    0.88
     exits
    0.87
     out
    0.85
    Exit
    0.83
     OUT
    0.82
     keluar
    0.81
    Activations Density 1.635%

    No Known Activations