© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15685
    Prev
    Next
    INDEX
    Explanations

    words related to virology, cellular biology and genetics

    oai_token-act-pair · gemini-2.0-flash

    Viral RNA/DNA/capsids

    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
    ⓧ
    -0.61
     незавершена
    -0.57
    AfterClass
    -0.57
     numberOfRows
    -0.57
     насељу
    -0.56
     Forward
    -0.55
     decompression
    -0.55
    حياتها
    -0.54
    Legături
    -0.54
     placement
    -0.54
    POSITIVE LOGITS
     intptr
    0.49
    ExecuteReader
    0.47
    ority
    0.46
    Indented
    0.45
    gine
    0.45
    ick
    0.45
    yati
    0.44
    ავ
    0.44
     gynhyrchwyd
    0.44
    licite
    0.44
    Activations Density 5.937%

    No Known Activations