© 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. 11164
    Prev
    Next
    INDEX
    Explanations

    scientific research texts about the biological effects of different substances and chemical species on cells, specifically focusing on cancer research.

    oai_token-act-pair · gemini-2.0-flash

    Cell lines A549 and H1975

    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
     diſt
    -0.66
     Monfieur
    -0.66
     houſe
    -0.66
     Houſe
    -0.65
     uſed
    -0.64
     myſelf
    -0.64
     firſt
    -0.63
    AsUp
    -0.62
     ſeveral
    -0.62
     Diſ
    -0.61
    POSITIVE LOGITS
    
    0.55
    FunctionFlags
    0.54
    httphttps
    0.51
    numerusform
    0.50
    AnchorStyles
    0.49
    Према
    0.47
    ]-->
    0.46
    WithMany
    0.46
     aapt
    0.46
    }}}{\
    0.45
    Activations Density 2.234%

    No Known Activations