© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 673
    Prev
    Next
    INDEX
    Explanations

    phrases related to the integrity, impartiality, and proper functioning of the judiciary and democratic institutions

    oai_token-act-pair · gemini-2.0-flash

    Impartiality and justice

    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
     uLocal
    -0.56
     graphique
    -0.56
    SequentialGroup
    -0.56
     graphiques
    -0.56
    órmula
    -0.55
     itſelf
    -0.55
     typelib
    -0.53
     Monfieur
    -0.51
     Monro
    -0.51
    Pratique
    -0.51
    POSITIVE LOGITS
    nocache
    0.60
    IsInitialized
    0.56
    itzende
    0.54
     Infórmanos
    0.54
    PARATUS
    0.50
    ModelBuilder
    0.50
     geografic
    0.49
    InvalidProtocol
    0.48
     متعلقه
    0.48
    లాలు
    0.48
    Activations Density 2.974%

    No Known Activations