© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a past lack of knowledge

    oai_token-act-pair · gemini-2.0-flash

    words related to perception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ujednoznacz
    -0.50
    Erreferentziak
    -0.46
    StoryboardSegue
    -0.46
    BufferException
    -0.45
    COMMERCIAL
    -0.44
    makeText
    -0.44
    articulo
    -0.43
    openqa
    -0.43
    
    -0.43
    ondissement
    -0.42
    POSITIVE LOGITS
     seen
    1.10
     heard
    1.02
     saw
    0.96
    Seen
    0.94
     Seen
    0.90
    seen
    0.88
     SEEN
    0.85
     SAW
    0.82
    Saw
    0.81
    heard
    0.81
    Activations Density 1.214%

    No Known Activations