Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14450
    Prev
    Next
    INDEX
    Explanations

    text about the history of astronomy and related sciences

    oai_token-act-pair · gemini-2.0-flash

    academic/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    oia
    -0.49
     chisel
    -0.48
    Skocz
    -0.48
     cré
    -0.47
    holi
    -0.47
    tels
    -0.47
    header
    -0.46
     GoogleFonts
    -0.45
     protoimpl
    -0.45
     Mudd
    -0.44
    POSITIVE LOGITS
    يميديا
    0.59
    timis
    0.58
    rawDesc
    0.56
     ProtoMessage
    0.56
     transfieras
    0.54
    awtextra
    0.53
    DotNetBar
    0.52
     EClass
    0.50
    msgTypes
    0.50
    着用
    0.50
    Activations Density 3.158%

    No Known Activations