© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    mentions of cards, especially credit cards, ballot cards, or card games

    oai_token-act-pair · gemini-2.0-flash

    card

    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
     BoxDecoration
    -0.54
     EdgeInsets
    -0.51
    UnitTesting
    -0.49
    s
    -0.48
    (\
    -0.46
     marge
    -0.46
    decin
    -0.45
    reifen
    -0.45
    channel
    -0.44
    StringVar
    -0.44
    POSITIVE LOGITS
    EndGlobalSection
    0.67
    IUrlHelper
    0.65
    "):
    0.65
    +:+
    0.63
     lenker
    0.62
    ніципа
    0.60
    ")){
    0.60
    nasium
    0.59
    GEBURTS
    0.58
    "));
    0.58
    Activations Density 1.805%

    No Known Activations