© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating action, validation or transfer of information from one entity to another, often in official or regulated contexts

    oai_token-act-pair · gemini-2.0-flash

    pass

    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
     passes
    -1.27
     Passing
    -1.24
    passing
    -1.23
    Passing
    -1.23
     pass
    -1.23
     passing
    -1.23
     passed
    -1.22
    passed
    -1.22
     Passes
    -1.19
     Passed
    -1.14
    POSITIVE LOGITS
    ρω
    0.49
     starting
    0.48
     beginning
    0.45
     using
    0.45
     từ
    0.42
     mulai
    0.41
     ray
    0.41
     terecht
    0.41
    чо
    0.40
     rife
    0.40
    Activations Density 37.062%

    No Known Activations