© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11716
    Prev
    Next
    INDEX
    Explanations

    code artifacts like register names and signal names

    oai_token-act-pair · gemini-2.0-flash

    Code/configuration settings

    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
    losis
    -0.56
    Искәрмәләр
    -0.55
    Referanser
    -0.54
    Rüyada
    -0.53
    Referències
    -0.50
     ModelExpression
    -0.50
     May
    -0.48
    듈
    -0.47
     Zusch
    -0.46
    ais
    -0.46
    POSITIVE LOGITS
     Efq
    0.80
     itſelf
    0.77
     faſt
    0.73
     myſelf
    0.73
    ſelf
    0.71
     ſmall
    0.70
     Diſ
    0.70
     pleaſure
    0.69
     purpoſe
    0.69
     Jefus
    0.69
    Activations Density 0.893%

    No Known Activations