© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11239
    Prev
    Next
    INDEX
    Explanations

    spanish words or code containing spanish words related to program flow

    oai_token-act-pair · gemini-2.0-flash

    Spanish language

    np_max-act · gemini-2.0-flash

    say "Spanish"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ValueStyle
    -0.86
    PreferredItem
    -0.76
    <bos>
    -0.74
     ExecuteAsync
    -0.73
    protoimpl
    -0.67
    LookAnd
    -0.66
     cherchés
    -0.65
     Administrativna
    -0.65
    ônicos
    -0.63
    )‏
    -0.62
    POSITIVE LOGITS
     pierdas
    0.58
     elástica
    0.57
     anisotropy
    0.54
     eller
    0.53
     carbons
    0.52
     или
    0.52
    mole
    0.51
    Elec
    0.51
     invertebrate
    0.51
    casus
    0.51
    Activations Density 0.191%

    No Known Activations