© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9640
    Prev
    Next
    INDEX
    Explanations

    mentions of physical cards, especially credit cards, and in some cases things related to the heart

    oai_token-act-pair · gemini-2.0-flash

    card-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     card
    -0.63
     candle
    -0.54
    gdx
    -0.53
    Card
    -0.52
     paper
    -0.52
     Card
    -0.51
    culoskeletal
    -0.50
     kart
    -0.49
    card
    -0.49
     CARD
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.73
     typelib
    0.58
    viewDidLoad
    0.57
     تضيفلها
    0.56
    })));
    0.56
    UnusedPrivate
    0.55
     nahilalakip
    0.54
    awaiter
    0.54
    Sklici
    0.54
     obstante
    0.53
    Activations Density 2.390%

    No Known Activations