© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5667
    Prev
    Next
    INDEX
    Explanations

    strong or mild positive or negative opinions

    oai_token-act-pair · gemini-2.0-flash

    about, aspect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     AttributeSet
    -0.57
     SafeMath
    -0.54
    transQ
    -0.54
    XmlEnum
    -0.50
     EconPapers
    -0.50
    RefNanny
    -0.48
    setRotation
    -0.47
    ($__
    -0.45
    IBU
    -0.45
    dataTables
    -0.44
    POSITIVE LOGITS
     about
    1.08
     aspect
    0.87
    about
    0.82
    aspect
    0.80
     thing
    0.75
     ABOUT
    0.70
     aspects
    0.68
    About
    0.66
     About
    0.66
     tentang
    0.66
    Activations Density 0.713%

    No Known Activations