© 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. 281
    Prev
    Next
    INDEX
    Explanations

    language related to state or federal grants and funding

    oai_token-act-pair · gemini-2.0-flash

    federal

    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
    StoryboardSegue
    -0.61
    BeginContext
    -0.56
     pageContext
    -0.53
     Assignee
    -0.50
    TestingModule
    -0.49
    uxxxx
    -0.48
    esteld
    -0.47
    setAccessible
    -0.47
    __':
    -0.46
    isateurs
    -0.46
    POSITIVE LOGITS
     InputDecoration
    0.63
    itola
    0.56
     EdgeInsets
    0.55
     désolés
    0.54
     مرئيه
    0.52
     گوش
    0.52
    ngo
    0.52
    ult
    0.52
    LLocation
    0.51
     pinulongan
    0.51
    Activations Density 2.624%

    No Known Activations