© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10446
    Prev
    Next
    INDEX
    Explanations

    words semantically related to doing or getting something either physically or digitally.

    oai_token-act-pair · gemini-2.0-flash

    Actions and processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     يتيمه
    -0.77
     photolibrary
    -0.76
    AndEndTag
    -0.75
     المعيارى
    -0.75
    AddTagHelper
    -0.74
     itſelf
    -0.73
     Efq
    -0.73
    EDEFAULT
    -0.70
     Houſe
    -0.69
     esternos
    -0.68
    POSITIVE LOGITS
     a
    0.86
     the
    0.75
     an
    0.75
     your
    0.61
     my
    0.59
     vol
    0.57
     them
    0.57
     all
    0.56
     particular
    0.55
     and
    0.54
    Activations Density 5.150%

    No Known Activations