© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 294
    Prev
    Next
    INDEX
    Explanations

    JSON data structures and related keywords

    oai_token-act-pair · gemini-2.0-flash

    code and technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    interopRequire
    -0.59
    체
    -0.52
     تضيفلها
    -0.52
    GOTREF
    -0.50
    noticia
    -0.48
    errHandler
    -0.47
     esternos
    -0.46
     mon
    -0.46
    WebElementEntity
    -0.46
    matchCondition
    -0.46
    POSITIVE LOGITS
     InputDecoration
    0.65
     itſelf
    0.64
     fubject
    0.62
     becauſe
    0.61
     vPvB
    0.61
     Jefus
    0.60
     himſelf
    0.59
    
    0.59
     XNUMX
    0.59
     Chriftian
    0.58
    Activations Density 2.949%

    No Known Activations