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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14541
    Prev
    Next
    INDEX
    Explanations

    Spanish language and cultural references

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    РЭ
    -0.60
    наче
    -0.57
    }")
    
    -0.52
     newBuilder
    -0.49
    beginTransaction
    -0.48
    '][]
    -0.48
    คนที่
    -0.47
     person
    -0.47
     >>=
    -0.46
    urator
    -0.46
    POSITIVE LOGITS
    TagHelpers
    0.72
     obispo
    0.60
     discí
    0.58
     senador
    0.58
     soldado
    0.57
     fotógrafo
    0.57
     ailes
    0.56
     filósofo
    0.56
     arquitecto
    0.56
     animali
    0.55
    Activations Density 1.087%

    No Known Activations