© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to dogs and/or sexual acts involving men and dogs

    oai_token-act-pair · 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
     Rost
    -0.50
     trans
    -0.49
     Template
    -0.48
    TEMPLATE
    -0.48
     template
    -0.48
    征
    -0.48
     Deficit
    -0.47
    ICKNESS
    -0.46
     templates
    -0.46
     Tubes
    -0.45
    POSITIVE LOGITS
     dogs
    1.41
     dog
    1.31
    Dogs
    1.27
     Dogs
    1.27
    Dog
    1.22
     canine
    1.20
     DOG
    1.19
    dog
    1.17
     Dog
    1.14
     DOGS
    1.11
    Activations Density 0.271%

    No Known Activations