© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5568
    Prev
    Next
    INDEX
    Explanations

    mostly random words that only sometimes correspond to the topic of healthcare

    oai_token-act-pair · gemini-2.0-flash

    Words for "no"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     متعلقه
    -0.90
    featureID
    -0.88
     препратки
    -0.87
     nakalista
    -0.85
     оригіналу
    -0.84
    PerformLayout
    -0.83
     فريبيس
    -0.80
    \{\\
    -0.75
    rungsseite
    -0.75
    >",
    -0.75
    POSITIVE LOGITS
     not
    1.59
     não
    1.48
     tidak
    1.44
     doesn
    1.36
     didn
    1.34
     nicht
    1.32
     niet
    1.31
     no
    1.24
     không
    1.22
     не
    1.21
    Activations Density 2.512%

    No Known Activations