© 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. 8612
    Prev
    Next
    INDEX
    Explanations

    words that are either medical or related to the failure of something

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     chrétiens
    -0.66
     stället
    -0.64
     dieux
    -0.64
     varandra
    -0.63
     refroid
    -0.62
     découver
    -0.62
     fermés
    -0.62
     avoient
    -0.60
     étoient
    -0.60
     pères
    -0.60
    POSITIVE LOGITS
     ProtoMessage
    0.30
     estekak
    0.27
     Arabs
    0.27
     kasarigan
    0.26
    httphttps
    0.26
     Banach
    0.25
     Schengen
    0.25
     Italians
    0.25
     Esau
    0.25
     Platon
    0.24
    Activations Density 3.512%

    No Known Activations