© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6329
    Prev
    Next
    INDEX
    Explanations

    hate speech or racist language.

    oai_token-act-pair · gemini-2.0-flash

    romantic relationship terms

    np_token-act-pair-logits · gpt-4o-mini

    Dating and relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     виправивши
    -0.84
    RetentionPolicy
    -0.78
    
    -0.73
    ValueStyle
    -0.71
     tartalomajánló
    -0.69
     дописавши
    -0.68
     bezeichneter
    -0.67
    fromnode
    -0.65
     RouterModule
    -0.64
    XmlAccessType
    -0.63
    POSITIVE LOGITS
     marry
    1.03
     slept
    0.96
     dating
    0.96
     date
    0.96
     sleep
    0.95
     dated
    0.94
     marrying
    0.93
     Date
    0.88
     sleeps
    0.87
     sleeping
    0.86
    Activations Density 2.555%

    No Known Activations