© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16023
    Prev
    Next
    INDEX
    Explanations

    words associated with religious choirs and scientific genes

    oai_token-act-pair · gemini-2.0-flash

    director

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     gene
    -1.07
     genes
    -0.99
    Gene
    -0.91
    gene
    -0.90
     Genes
    -0.90
     transcript
    -0.89
     Gene
    -0.86
    Genes
    -0.85
    genes
    -0.81
     transcrip
    -0.79
    POSITIVE LOGITS
     director
    0.67
    Director
    0.65
     Director
    0.65
     Directors
    0.64
     directors
    0.63
    director
    0.63
     DIRECTOR
    0.60
     Réponses
    0.60
     الرياضيه
    0.60
    Direct
    0.57
    Activations Density 2.014%

    No Known Activations