© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15468
    Prev
    Next
    INDEX
    Explanations

    a mix of words and phrases related to conflict, mathematics, recreation, or race

    oai_token-act-pair · gemini-2.0-flash

    Varied topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.85
    ArgsConstructor
    -0.71
     leaſt
    -0.59
    Notae
    -0.56
     Houſe
    -0.54
    fois
    -0.52
    ÂN
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     Anſ
    -0.51
    ScopeManager
    -0.49
    POSITIVE LOGITS
    IsContent
    0.67
    EndInit
    0.60
     AssemblyCompany
    0.55
    asteroide
    0.54
    StructEnd
    0.54
    }],
    0.52
    PreferredItem
    0.52
    UnsafeEnabled
    0.52
    
    0.51
     spins
    0.50
    Activations Density 0.748%

    No Known Activations