© 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. 11600
    Prev
    Next
    INDEX
    Explanations

    dates and references to figures and tables

    oai_token-act-pair · gemini-2.0-flash

    Months and days

    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
    FormTagHelper
    -0.73
    }{*}{}
    -0.72
    addGap
    -0.67
     kasarigan
    -0.65
    onsored
    -0.63
    enumi
    -0.63
     onPostExecute
    -0.59
    ImageContext
    -0.58
     requestCode
    -0.58
    ThroughAttribute
    -0.57
    POSITIVE LOGITS
    Host
    0.49
    host
    0.49
     HOST
    0.49
     transfieras
    0.48
    rlrl
    0.47
     host
    0.46
     Host
    0.46
     jist
    0.46
     paint
    0.44
    writeField
    0.44
    Activations Density 2.908%

    No Known Activations