© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7725
    Prev
    Next
    INDEX
    Explanations

    mentions of CSS files

    oai_token-act-pair · gemini-2.0-flash

    css

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     resourceCulture
    -1.00
     NSCoder
    -0.85
    原始内容存档于
    -0.79
     MainAxisSize
    -0.69
    InputBorder
    -0.65
     protoimpl
    -0.65
    TagHelper
    -0.62
     gar
    -0.60
    addGap
    -0.60
     nic
    -0.60
    POSITIVE LOGITS
     dénon
    0.96
     culturelles
    0.95
     auroit
    0.93
     feroit
    0.90
     colère
    0.89
     avoient
    0.84
     automatiques
    0.84
     dévelo
    0.84
     grève
    0.84
     preghiera
    0.84
    Activations Density 0.827%

    No Known Activations