Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2146
    Prev
    Next
    INDEX
    Explanations

    technical and historical descriptions of cars from the late 1960s and early 1970s

    oai_token-act-pair · gemini-2.0-flash

    part numbers or identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     invokingState
    -0.50
    viewDidLoad
    -0.50
    Демографія
    -0.50
     remb
    -0.47
    ంక
    -0.46
    Xna
    -0.45
     componentes
    -0.45
     Komponenten
    -0.45
    PMD
    -0.45
    รม
    -0.44
    POSITIVE LOGITS
    featureID
    0.67
    
    0.55
    \}=
    0.55
     SUV
    0.54
     gazelle
    0.54
    oupe
    0.53
     iVar
    0.53
     SUVs
    0.52
    ôtel
    0.52
     postIndex
    0.52
    Activations Density 8.162%

    No Known Activations