© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11243
    Prev
    Next
    INDEX
    Explanations

    words, numbers, or phrases that act as discourse markers, references to earlier statements, or connections between sentences.

    oai_token-act-pair · gemini-2.0-flash

    reporting events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     <<<<<<<<<<<<<<
    -0.68
    /**
    -0.56
     kaarangay
    -0.56
     derail
    -0.54
    imread
    -0.52
    IActionResult
    -0.51
     MAINTENANCE
    -0.51
    Становништво
    -0.50
    发表于
    -0.50
     rebounds
    -0.50
    POSITIVE LOGITS
     itſelf
    0.61
    antaranya
    0.60
     purpoſe
    0.59
     raiſ
    0.58
     uſe
    0.54
     perſon
    0.54
     themſelves
    0.53
     dalamnya
    0.52
     perfons
    0.52
     himſelf
    0.51
    Activations Density 3.606%

    No Known Activations