© 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. 10274
    Prev
    Next
    INDEX
    Explanations

    code or file related tags and syntax

    oai_token-act-pair · 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
    fastjson
    -0.46
    posedge
    -0.42
    ↵
    -0.41
    artifactId
    -0.41
    rino
    -0.41
    :
    -0.41
     su
    -0.40
    \#:
    -0.39
     sur
    -0.39
     :
    -0.38
    POSITIVE LOGITS
    AnimationsModule
    0.78
     Biôgrafia
    0.77
    ISupport
    0.75
     الحره
    0.75
     NSCoder
    0.74
    RenderAtEndOf
    0.74
    bbene
    0.72
    ViewFeatures
    0.71
    期刊论文
    0.69
     Theſe
    0.67
    Activations Density 18.925%

    No Known Activations