© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1429
    Prev
    Next
    INDEX
    Explanations

    phrases including names of popular commercial products and works of fiction

    oai_token-act-pair · gemini-2.0-flash

    events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ২০১
    -0.47
     "{
    -0.46
    -0.45
    -0.42
    рованного
    -0.42
    -0.40
    -0.40
     parto
    -0.40
    wohner
    -0.40
    之处
    -0.40
    POSITIVE LOGITS
    AsUp
    0.81
    expandindo
    0.74
     HasFactory
    0.74
     protoimpl
    0.71
    出版年
    0.69
     '\\;'
    0.69
    曖昧さ回避
    0.68
    Nazionale
    0.65
    الحياه
    0.65
    LookAnd
    0.65
    Activations Density 20.059%

    No Known Activations