© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3018
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets and spanish/portuguese words

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act-logits · gemini-2.0-flash

    Spanish

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Bergamo
    -0.50
     Ancona
    -0.49
     م
    -0.47
     س
    -0.47
     ب
    -0.46
     ص
    -0.46
     ک
    -0.46
     ت
    -0.43
     Krakow
    -0.43
     Seville
    -0.42
    POSITIVE LOGITS
     orgánica
    0.65
    antaranya
    0.61
     fotográfica
    0.60
     vectoriales
    0.60
     inmediata
    0.59
     geomé
    0.59
     extranjera
    0.59
     colgantes
    0.58
     táctil
    0.58
    êcher
    0.57
    Activations Density 1.432%

    No Known Activations