© 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. 14004
    Prev
    Next
    INDEX
    Explanations

    instances of currencies and numbers

    oai_token-act-pair · gemini-2.0-flash

    currencies and financial transactions

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

    currency names

    np_max-act-logits · gemini-2.0-flash

    say currency Method used: 2 — tokens after indicate currency/money words — say currency

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    //
    -0.75
    argli
    -0.66
    minecraftforge
    -0.64
    illai
    -0.61
    conci
    -0.61
    ربای
    -0.59
     HasFactory
    -0.59
    falgar
    -0.58
     Sopho
    -0.58
    MockMvc
    -0.58
    POSITIVE LOGITS
     đồng
    0.67
     pes
    0.53
     TRY
    0.50
     kron
    0.46
     won
    0.46
    rub
    0.46
     Pes
    0.45
     rup
    0.45
    Manbalar
    0.43
     den
    0.43
    Activations Density 1.268%

    No Known Activations