© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10357
    Prev
    Next
    INDEX
    Explanations

    words related to scientific and technical documentation and academic writing

    oai_token-act-pair · gemini-2.0-flash

    programming, scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    sizeCache
    -1.09
     CreateTagHelper
    -0.82
    oa̍t
    -0.72
     مشين
    -0.70
    Personendaten
    -0.69
     MenuView
    -0.68
    出版年
    -0.66
    ModelAdmin
    -0.66
    LoggerFactory
    -0.64
    Становништво
    -0.64
    POSITIVE LOGITS
     Vide
    0.54
     sema
    0.53
     Send
    0.47
    Vide
    0.45
     heavy
    0.45
    principalTable
    0.45
    emas
    0.44
    Shady
    0.44
     Vikipedi
    0.44
    primento
    0.43
    Activations Density 12.078%

    No Known Activations