© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12933
    Prev
    Next
    INDEX
    Explanations

    academic publications and related terms like proceedings, conferences, and journals

    oai_token-act-pair · gemini-2.0-flash

    Proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    tvguidetime
    -0.59
    Laravel
    -0.59
     AppColors
    -0.58
    alyptus
    -0.58
     reinforcing
    -0.55
    olute
    -0.55
     circumvent
    -0.54
     recipro
    -0.53
     sandero
    -0.53
    medy
    -0.52
    POSITIVE LOGITS
    клопе
    0.76
    BeginContext
    0.64
    
    0.60
    XmlAccessType
    0.58
    LookAnd
    0.53
    TagMode
    0.53
    ؤية
    0.52
     iprot
    0.52
    MeasureSpec
    0.51
    writeField
    0.50
    Activations Density 2.480%

    No Known Activations