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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4763
    Prev
    Next
    INDEX
    Explanations

    expressions related to wanting or liking something, combined with pharmaceutical or medical terms and online commerce

    oai_token-act-pair · gemini-2.0-flash

    code and technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    PyExc
    -0.52
    oa̍t
    -0.48
     gyhoeddwyd
    -0.47
    rungsseite
    -0.47
    esModule
    -0.47
    lapsingToolbar
    -0.46
    expandindo
    -0.44
    antis
    -0.43
     Italijanski
    -0.42
    opengl
    -0.41
    POSITIVE LOGITS
     الحره
    0.67
     Conſ
    0.67
     convenable
    0.62
     OnInit
    0.60
     becauſe
    0.59
     iconLine
    0.58
    Становништво
    0.57
     TextInputType
    0.56
    BibitemShut
    0.56
     resourceCulture
    0.55
    Activations Density 0.169%

    No Known Activations