© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7070
    Prev
    Next
    INDEX
    Explanations

    words used in science, particularly chemistry

    oai_token-act-pair · gemini-2.0-flash

    chemical reactions/compounds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     تضيفلها
    -1.02
    protoimpl
    -0.90
     resourceCulture
    -0.88
    DockStyle
    -0.86
     للاسماء
    -0.84
    UnusedPrivate
    -0.83
     myſelf
    -0.83
     externi
    -0.81
     ExecuteAsync
    -0.78
    InjectAttribute
    -0.77
    POSITIVE LOGITS
     free
    0.48
    gren
    0.47
    VersionUID
    0.47
     la
    0.46
     opening
    0.44
    시오
    0.43
    cine
    0.42
     pieds
    0.42
    ssch
    0.40
     char
    0.40
    Activations Density 1.924%

    No Known Activations