© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14412
    Prev
    Next
    INDEX
    Explanations

    words related to studies or data, medical procedures, transportation, wrestling matches, food production, furniture, trails and routes

    oai_token-act-pair · gemini-2.0-flash

    Transportation and patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AxisAlignment
    -0.75
    bonucleic
    -0.69
    multirow
    -0.56
    albert
    -0.56
     muualla
    -0.56
    PageRoute
    -0.54
    manni
    -0.53
    $$\
    -0.53
    centerY
    -0.52
     kotlinx
    -0.52
    POSITIVE LOGITS
    <bos>
    0.88
    stoke
    0.50
     tearDown
    0.50
     pleaſure
    0.49
    ſelf
    0.49
    //
    0.48
     ―――――
    0.48
     cdti
    0.48
    Rptr
    0.47
     Italijani
    0.47
    Activations Density 8.566%

    No Known Activations