© 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. 3946
    Prev
    Next
    INDEX
    Explanations

    dates containing with the numbers 3,7,8 and possibly also Malay words, but probably mostly dates

    oai_token-act-pair · gemini-2.0-flash

    7

    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
     acrylique
    -0.65
     noDo
    -0.58
     femininas
    -0.56
     bílá
    -0.55
     citoy
    -0.54
     vectorielle
    -0.52
     fermés
    -0.52
     vectorielles
    -0.51
     dø
    -0.51
     Italij
    -0.51
    POSITIVE LOGITS
     AttributeSet
    0.77
     Wikimedijinoj
    0.73
     BeautifulSoup
    0.64
    AddTagHelper
    0.61
     TestBed
    0.60
    Gön
    0.60
     متعلقه
    0.60
    masing
    0.59
     Arboretum
    0.57
    jgl
    0.56
    Activations Density 0.563%

    No Known Activations