© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7985
    Prev
    Next
    INDEX
    Explanations

    spanish language questions, potentially related to Javascript

    oai_token-act-pair · gemini-2.0-flash

    base

    np_max-act · gemini-2.0-flash

    Spanish words

    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
     âgées
    -0.67
     المعيارى
    -0.58
     proposons
    -0.56
     récompenses
    -0.54
     resten
    -0.54
     című
    -0.52
     ruines
    -0.51
     anciennes
    -0.51
     decoracion
    -0.51
     meubles
    -0.50
    POSITIVE LOGITS
     ſte
    0.73
     ſta
    0.72
    __":
    0.71
     Shor
    0.68
    fortawesome
    0.68
     raiſ
    0.67
     faſt
    0.66
     ſche
    0.66
    styleType
    0.64
     ſch
    0.64
    Activations Density 0.172%

    No Known Activations