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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4993
    Prev
    Next
    INDEX
    Explanations

    section titles, proper names, and words related to stages and periods

    oai_token-act-pair · gemini-2.0-flash

    Stage or Period

    np_max-act · gemini-2.0-flash

    Period

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Stage
    -1.15
     Version
    -1.15
     Phase
    -1.08
     Level
    -1.06
     Category
    -1.05
     Period
    -1.04
     Option
    -1.02
     Phases
    -1.02
     Segment
    -1.01
     Line
    -1.00
    POSITIVE LOGITS
    WebControls
    0.85
     position
    0.83
     number
    0.79
     area
    0.76
     type
    0.72
    TagMode
    0.71
     structure
    0.71
    WaitGroup
    0.70
     place
    0.69
     range
    0.69
    Activations Density 6.131%

    No Known Activations