© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1456
    Prev
    Next
    INDEX
    Explanations

    words related to judging quality and safety, especially in an official sense

    oai_token-act-pair · gemini-2.0-flash

    ratings and assessments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AccessorTable
    -0.65
    ánto
    -0.64
    AutoScaleMode
    -0.63
    مقاله
    -0.63
    новништво
    -0.62
    LayoutPanel
    -0.60
    QMetaType
    -0.59
     réus
    -0.58
     wrongs
    -0.58
    principalColumn
    -0.57
    POSITIVE LOGITS
     code
    0.48
     Level
    0.47
     high
    0.47
    要不是
    0.45
    copo
    0.45
     Code
    0.44
     level
    0.44
    тельство
    0.44
     C
    0.43
     highest
    0.43
    Activations Density 1.691%

    No Known Activations