© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4139
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs and lemmas

    oai_token-act-pair · gemini-2.0-flash

    induction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mínima
    -0.56
    ooplankton
    -0.54
     Dunes
    -0.50
     calitate
    -0.49
     dunes
    -0.49
     Yud
    -0.49
     Wetlands
    -0.48
     forceps
    -0.48
     heretics
    -0.47
    Produzione
    -0.47
    POSITIVE LOGITS
    <bos>
    0.91
    ImageContext
    0.63
    styleUrls
    0.63
     useRouter
    0.60
    Affirmed
    0.60
    CompleteListener
    0.58
     viewDidLoad
    0.58
    interopRequire
    0.57
     HttpNotFound
    0.57
     travel
    0.56
    Activations Density 1.692%

    No Known Activations