© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1713
    Prev
    Next
    INDEX
    Explanations

    C# "using" statements for core libraries like System.Collections and System.Threading

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
    <bos>
    -0.73
     VIDEOTAPE
    -0.37
     상세
    -0.36
    gel
    -0.35
    gar
    -0.34
    gg
    -0.33
    jem
    -0.33
    bes
    -0.33
    pra
    -0.33
    va
    -0.32
    POSITIVE LOGITS
     Efq
    0.47
     pleaſure
    0.43
    /**
    0.43
     ſtate
    0.43
     myſelf
    0.43
     itſelf
    0.43
     purpoſe
    0.42
     Majefty
    0.41
     themſelves
    0.40
     Jefus
    0.40
    Activations Density 0.118%

    No Known Activations