© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 1028
    Prev
    Next
    INDEX
    Explanations

    tokens describing the transition of people from one position (e.g., student) to another (e.g. credible source).

    oai_token-act-pair · gemini-2.0-flash

    Creative works and people

    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
    DockStyle
    -0.75
    invokeLater
    -0.59
    Rè
    -0.49
     LoggerFactory
    -0.49
    Tikang
    -0.48
    цездатний
    -0.47
    FOOTNOTES
    -0.47
     dentelle
    -0.47
     tearDown
    -0.47
    tvguidetime
    -0.44
    POSITIVE LOGITS
     story
    1.08
    Story
    1.01
     Story
    1.01
    story
    0.96
     STORY
    0.90
    aarrggbb
    0.80
    STORY
    0.76
     Sham
    0.61
    abspath
    0.60
     sha
    0.59
    Activations Density 2.821%

    No Known Activations