© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names consisting of several parts

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    tonode
    -0.58
    Layers
    -0.53
         
    -0.51
    الإنجليزية
    -0.49
    SizeF
    -0.49
       
    -0.48
    تق
    -0.48
     censi
    -0.48
     push
    -0.48
     DRINK
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.65
    وأضاف
    0.64
    JvmStatic
    0.59
    titleMargin
    0.59
     suor
    0.53
    rungsseite
    0.52
     paramString
    0.52
    例句
    0.52
     informée
    0.52
    CollectionUtils
    0.49
    Activations Density 1.239%

    No Known Activations