© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15703
    Prev
    Next
    INDEX
    Explanations

    scientific language regarding cell and tissue biology, mostly from cancer research

    oai_token-act-pair · gemini-2.0-flash

    epithelial cell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    بوابة
    -0.78
    setupUi
    -0.62
     <=",
    -0.59
    帖最后由
    -0.56
    endforeach
    -0.56
    Décès
    -0.56
    --*/
    -0.55
    MemoryWarning
    -0.54
    хьтан
    -0.53
     ritratto
    -0.52
    POSITIVE LOGITS
     GetEnumerator
    0.48
    featureID
    0.47
     invasive
    0.46
    AutoScale
    0.45
    culada
    0.45
    󠁣
    0.44
    acqu
    0.44
     Hidro
    0.44
     secretaries
    0.43
    tabular
    0.43
    Activations Density 4.389%

    No Known Activations