© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10359
    Prev
    Next
    INDEX
    Explanations

    words related to electrical current and electronic devices

    oai_token-act-pair · gemini-2.0-flash

    failure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    fortawesome
    -0.62
     '\\;'
    -0.61
    DrawerToggle
    -0.60
    الدراسه
    -0.60
     kasarigan
    -0.59
    Xna
    -0.59
    FormTagHelper
    -0.56
    ImageField
    -0.56
     disponibilités
    -0.55
     betweenstory
    -0.55
    POSITIVE LOGITS
     failure
    0.57
     failures
    0.52
    timewa
    0.51
    failures
    0.50
    ayage
    0.48
    جستارهای
    0.47
    failure
    0.46
     Failure
    0.46
     pulumi
    0.45
     fail
    0.44
    Activations Density 1.866%

    No Known Activations