© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5305
    Prev
    Next
    INDEX
    Explanations

    words from a non-English language that are code snippets or documentation related Python streams

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · 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
     ollut
    -0.91
    parsedMessage
    -0.80
    richTextPanel
    -0.73
    ArgsConstructor
    -0.66
     realizzato
    -0.63
     незавершена
    -0.63
     utafitiHapana
    -0.61
     którą
    -0.61
     stato
    -0.60
     мәкал
    -0.59
    POSITIVE LOGITS
    хова
    0.61
    <?,
    0.55
    Datuak
    0.54
     corta
    0.53
     firma
    0.51
    scalatest
    0.49
    ilha
    0.49
    ecta
    0.49
    сова
    0.48
     rile
    0.48
    Activations Density 0.392%

    No Known Activations