© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 75
    Prev
    Next
    INDEX
    Explanations

    the word "head" and related words or associated concepts.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     heads
    -2.92
     head
    -2.81
     Head
    -2.78
     Heads
    -2.78
     HEAD
    -2.77
    Head
    -2.72
    heads
    -2.70
    head
    -2.64
    HEAD
    -2.64
    Heads
    -2.61
    POSITIVE LOGITS
     насељу
    0.49
    Identyfik
    0.47
     通販
    0.46
    /******/
    0.42
    кобрита
    0.41
    Према
    0.40
    
    0.40
     saites
    0.39
     touché
    0.39
     Benjamin
    0.39
    Activations Density 2.921%

    No Known Activations