© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    words related to time, scientific studies, agriculture, and natural habitats

    oai_token-act-pair · gemini-2.0-flash

    food or nature

    np_max-act-logits · gemini-2.0-flash
    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
     وتسجيلات
    -0.65
    BeginContext
    -0.60
    MemoryWarning
    -0.59
     nahilalakip
    -0.58
    Hentet
    -0.55
    Kilder
    -0.55
     terecht
    -0.54
     يتيمه
    -0.54
    cemment
    -0.53
     IBOutlet
    -0.53
    POSITIVE LOGITS
     lobsters
    0.71
     pyrite
    0.67
     oysters
    0.66
     magma
    0.65
     apples
    0.64
     pears
    0.63
     fires
    0.63
     wells
    0.63
     crows
    0.63
     oaks
    0.63
    Activations Density 12.746%

    No Known Activations