© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16193
    Prev
    Next
    INDEX
    Explanations

    CLI commands like "list", "show", or "get".

    oai_token-act-pair · gemini-2.0-flash

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    CloseOperation
    -0.73
    HasAnnotation
    -0.63
    InputTagHelper
    -0.59
    VIAF
    -0.59
    complexContent
    -0.59
    bootstrapcdn
    -0.59
     canadensis
    -0.56
     NSCoder
    -0.54
    prnewswire
    -0.54
    MENAFN
    -0.53
    POSITIVE LOGITS
     map
    0.52
    JTable
    0.51
     مشين
    0.50
     mapping
    0.49
    listFiles
    0.47
     pageable
    0.47
     INTERESAR
    0.46
     list
    0.45
     laid
    0.45
    тності
    0.45
    Activations Density 1.586%

    No Known Activations