© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8394
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation, code snippets, and certain phrases that indicate a break in natural language or the start of a new topic.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     He
    -0.63
     On
    -0.60
     Is
    -0.54
     They
    -0.52
     This
    -0.52
     That
    -0.51
     It
    -0.50
     Then
    -0.50
    On
    -0.48
    EndTag
    -0.48
    POSITIVE LOGITS
    setupUi
    0.52
     RIPRODUZIONE
    0.50
    cleaner
    0.50
    cocina
    0.50
    UDAD
    0.50
    Скачать
    0.50
    burberry
    0.49
    slee
    0.49
    yeezy
    0.49
    bootstrapcdn
    0.49
    Activations Density 20.413%

    No Known Activations