© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9659
    Prev
    Next
    INDEX
    Explanations

    capitalized words in political discussion, or capitalized words indicating shouting

    oai_token-act-pair · gemini-2.0-flash

    Negative prefixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    LookAnd
    -0.60
    NgModule
    -0.53
     CoreData
    -0.51
    θρω
    -0.49
    SqlClient
    -0.48
    seiti
    -0.48
    udière
    -0.48
     kwanza
    -0.47
    ">${
    -0.47
    partement
    -0.46
    POSITIVE LOGITS
     Mal
    0.84
     Mis
    0.83
    Mal
    0.79
    Mis
    0.77
    ILLE
    0.72
     Cor
    0.71
     mal
    0.69
     Dece
    0.68
    mal
    0.67
    Cor
    0.66
    Activations Density 10.473%

    No Known Activations