© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5855
    Prev
    Next
    INDEX
    Explanations

    language related to social issues and discrimination

    oai_token-act-pair · gemini-2.0-flash

    legal situation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RoutingModule
    -0.64
     initComponents
    -0.63
    HasForeignKey
    -0.60
     AppModule
    -0.59
    BeginContext
    -0.56
    
    -0.55
    TagHelper
    -0.54
    ్రామ
    -0.52
     onResponse
    -0.52
    AttributeSet
    -0.52
    POSITIVE LOGITS
     stopped
    0.77
     Stopped
    0.69
    stopped
    0.67
     stop
    0.62
    stop
    0.59
    Stop
    0.58
    ReusableCell
    0.57
     سكانية
    0.56
     Stop
    0.54
     <=",
    0.54
    Activations Density 4.204%

    No Known Activations