© 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. 12497
    Prev
    Next
    INDEX
    Explanations

    words related to commercial inventions, offers and scientific or technical terms

    oai_token-act-pair · gemini-2.0-flash

    descriptions

    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
     laiton
    -0.79
     Monfieur
    -0.72
    Rohy
    -0.71
     Jefus
    -0.68
     ་་
    -0.68
    BibitemShut
    -0.67
    ſelf
    -0.66
    〢
    -0.65
     EconPapers
    -0.65
     myſelf
    -0.65
    POSITIVE LOGITS
     specialised
    0.59
    organisation
    0.59
     characterised
    0.59
    organised
    0.59
     organised
    0.56
    الحياه
    0.56
     organisational
    0.56
     şi
    0.56
     realised
    0.55
     organisation
    0.54
    Activations Density 4.554%

    No Known Activations