© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16040
    Prev
    Next
    INDEX
    Explanations

    words having to do with physical objects

    oai_token-act-pair · gemini-2.0-flash

    Structures and objects

    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
    RunAsync
    -0.68
    Xna
    -0.66
     ExecuteAsync
    -0.63
    nocache
    -0.60
    Билгалдахарш
    -0.57
    లాలు
    -0.57
    libft
    -0.57
    الإنجليزية
    -0.57
    harusnya
    -0.55
    writeFieldEnd
    -0.54
    POSITIVE LOGITS
     gọn
    0.58
     spécifique
    0.55
     crossed
    0.54
     cursed
    0.54
    enderror
    0.52
    ercizio
    0.52
    utebol
    0.50
     intersected
    0.50
     set
    0.50
     setType
    0.50
    Activations Density 4.255%

    No Known Activations