© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9949
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with billiards and cue sports

    oai_token-act-pair · gemini-2.0-flash

    Unique/uncommon words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     متعلقه
    -1.18
    ########.
    -0.86
    PerformLayout
    -0.84
    ThroughAttribute
    -0.82
    forName
    -0.75
    SharedDtor
    -0.74
     jsPsych
    -0.72
    WriteBarrier
    -0.71
    tagHelperRunner
    -0.71
    HomeAsUpEnabled
    -0.71
    POSITIVE LOGITS
     maksi
    0.48
    world
    0.40
     INC
    0.40
     écl
    0.39
     lenker
    0.39
    check
    0.38
     maximum
    0.38
    WebVitals
    0.37
     pinulongan
    0.37
     sm
    0.36
    Activations Density 0.619%

    No Known Activations