© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate similarity or comparison

    oai_token-act-pair · gemini-2.0-flash

    Comparison, relating

    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
    Personensuche
    -0.70
    
    -0.61
    PreferredItem
    -0.60
    RectangleBorder
    -0.60
    oa̍t
    -0.60
    expandindo
    -0.59
    ChildScrollView
    -0.59
    PropertyGroup
    -0.59
     ujednoznacz
    -0.59
    GraphicsUnit
    -0.58
    POSITIVE LOGITS
    epar
    0.49
    ंदीखरीदारी
    0.48
    етесь
    0.46
     andererseits
    0.46
    הערות
    0.44
     pede
    0.42
     bestellt
    0.42
    晏
    0.42
    Vip
    0.41
    HttpFoundation
    0.40
    Activations Density 2.195%

    No Known Activations