© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9588
    Prev
    Next
    INDEX
    Explanations

    words related to mythology, holidays, and folklore

    oai_token-act-pair · gemini-2.0-flash

    legends and lore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     legend
    -0.67
     légende
    -0.66
     newOwner
    -0.59
     humaines
    -0.56
    afficheront
    -0.55
    谚
    -0.54
    AddTagHelper
    -0.54
    سخ
    -0.53
    NameInMap
    -0.53
     Legend
    -0.52
    POSITIVE LOGITS
    ContentAsync
    0.54
     תע
    0.48
     Sublime
    0.46
     ***/
    0.46
     Espec
    0.45
    — 
    0.45
     Copernicus
    0.45
    pture
    0.44
    ceros
    0.44
    ophilic
    0.43
    Activations Density 16.095%

    No Known Activations