© 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. 9708
    Prev
    Next
    INDEX
    Explanations

    technical words used in scientific papers or patents describing chemical processes or results

    oai_token-act-pair · gemini-2.0-flash

    Medical or scientific text

    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
     oil
    -2.08
     Oil
    -1.90
    oil
    -1.88
     OIL
    -1.84
    Oil
    -1.80
    OIL
    -1.61
     oils
    -1.61
     Oils
    -1.51
     Öl
    -1.46
     oily
    -1.41
    POSITIVE LOGITS
     صوتيه
    0.50
    DialogContent
    0.50
     Bloomington
    0.47
    Peru
    0.47
    irnov
    0.46
    tagHelperRunner
    0.44
    ItemModel
    0.44
    lawayo
    0.43
     Kilkenny
    0.43
    >//
    0.42
    Activations Density 2.280%

    No Known Activations