© 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. 5700
    Prev
    Next
    INDEX
    Explanations

    verbs in languages besides English, especially Spanish and Portuguese and French.

    oai_token-act-pair · gemini-2.0-flash

    non-English languages

    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
     comunicarse
    -1.31
     decirle
    -1.20
     mantenerse
    -1.20
     sentarse
    -1.13
     usarlo
    -1.13
     adaptarse
    -1.12
     unirse
    -1.09
     entrenar
    -1.09
     parvenir
    -1.08
     solucionar
    -1.06
    POSITIVE LOGITS
    rir
    0.87
     myſelf
    0.85
     Tomar
    0.78
     Tinker
    0.76
    <bos>
    0.73
     Pacer
    0.73
    afir
    0.73
    oser
    0.72
     acar
    0.72
     reaſon
    0.71
    Activations Density 0.378%

    No Known Activations