© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11000
    Prev
    Next
    INDEX
    Explanations

    spanish words related to math and programming

    oai_token-act-pair · gemini-2.0-flash

    Spanish language

    np_max-act · gemini-2.0-flash

    el/lo Method used: 1 — because MAX_ACTIVATING_TOKENS are Spanish articles — el/lo

    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
     and
    -0.52
    /
    -0.47
    <bos>
    -0.46
     Зачем
    -0.45
     зачем
    -0.45
     alguém
    -0.43
     with
    -0.42
     or
    -0.42
    ’
    -0.41
    راتيج
    -0.41
    POSITIVE LOGITS
     متعلقه
    1.05
    GEBURTSDATUM
    0.94
     Италијани
    0.94
    脚注の使い方
    0.91
    addCriterion
    0.90
     يتيمه
    0.84
    참고
    0.84
    UnitTesting
    0.83
     onCreateView
    0.81
     فريبيس
    0.81
    Activations Density 0.140%

    No Known Activations