© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5049
    Prev
    Next
    INDEX
    Explanations

    personal opinions, recommendations, and travel advisories

    oai_token-act-pair · gemini-2.0-flash

    avoid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Autoritní
    -0.52
     Rept
    -0.51
    umbang
    -0.50
    FunctionFlags
    -0.48
    DllImport
    -0.48
    GUILayout
    -0.47
    kmale
    -0.47
    Hentet
    -0.47
    :✨
    -0.47
    
    -0.46
    POSITIVE LOGITS
     avoid
    1.67
     avoided
    1.65
     avoiding
    1.63
     avoids
    1.56
    avoid
    1.50
     Avoid
    1.44
     avoidance
    1.41
    Avoid
    1.39
     Avoiding
    1.35
     AVOID
    1.23
    Activations Density 2.194%

    No Known Activations