© 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. 14124
    Prev
    Next
    INDEX
    Explanations

    terms related to biological experiments, especially sequencing and analysis

    oai_token-act-pair · gemini-2.0-flash

    genetic sequencing

    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
    LabelTagHelper
    -0.73
    AndEndTag
    -0.66
    tagHelperRunner
    -0.59
     femininas
    -0.57
    ंदीखरीदारी
    -0.56
    dowa
    -0.51
    جري
    -0.51
    utilisons
    -0.50
     Ludlow
    -0.50
     lumineuse
    -0.50
    POSITIVE LOGITS
    Hochspringen
    0.55
    ArgumentParser
    0.52
     prote
    0.52
    gex
    0.50
    setVerticalGroup
    0.49
     me
    0.48
    tay
    0.47
    KURZBESCHREIBUNG
    0.47
    وروبا
    0.45
    μή
    0.45
    Activations Density 4.200%

    No Known Activations