© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14032
    Prev
    Next
    INDEX
    Explanations

    mentions of people with privileged access to information, and the concept of knowledge

    oai_token-act-pair · gemini-2.0-flash

    data and knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    apimachinery
    -0.82
    principalTable
    -0.75
    Personensuche
    -0.59
    AspNetCore
    -0.55
    docker
    -0.55
     MaterialApp
    -0.52
    kubectl
    -0.52
     her
    -0.52
    Docker
    -0.50
     Cap
    -0.48
    POSITIVE LOGITS
    }`).
    0.77
    脚注の使い方
    0.71
    帖最后由
    0.66
    InitVars
    0.65
    więcej
    0.63
     houſe
    0.63
     boycot
    0.62
     ſtate
    0.59
    bliss
    0.59
    elesai
    0.58
    Activations Density 1.168%

    No Known Activations