© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14925
    Prev
    Next
    INDEX
    Explanations

    latex array environments or xml style version and artifact id markup

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     +
    -0.59
     –
    -0.56
     (
    -0.52
    ,
    -0.51
    .
    -0.50
     kon
    -0.49
     am
    -0.48
     da
    -0.48
     >
    -0.45
     =
    -0.45
    POSITIVE LOGITS
     itſelf
    1.24
     myſelf
    1.16
    IntoConstraints
    1.14
     purpoſe
    1.02
    RectangleBorder
    1.02
     InputDecoration
    1.01
     houſe
    0.99
     pleaſure
    0.99
     uſe
    0.99
     himſelf
    0.99
    Activations Density 2.871%

    No Known Activations