© 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. 11803
    Prev
    Next
    INDEX
    Explanations

    words related to programming with a slight preference for the Spanish language

    oai_token-act-pair · gemini-2.0-flash

    Spanish, "want" or "need"

    np_max-act · gemini-2.0-flash
    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
    讓你
    -0.62
    )(((
    -0.62
    谢谢你
    -0.61
     باشیم
    -0.60
     давайте
    -0.60
     będziemy
    -0.58
    讓我們
    -0.57
     будешь
    -0.57
    让我们
    -0.57
    讓我
    -0.57
    POSITIVE LOGITS
    原始内容存档于
    0.90
     Romains
    0.88
     peindre
    0.88
     térmico
    0.80
     grossesse
    0.80
     Grecs
    0.80
     détru
    0.78
     étrangère
    0.78
     dépens
    0.78
     réfugi
    0.77
    Activations Density 0.755%

    No Known Activations