© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7657
    Prev
    Next
    INDEX
    Explanations

    descriptions of people's appearance

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    DockStyle
    -0.71
    évaluateur
    -0.68
    uxxxx
    -0.64
     umane
    -0.62
     humains
    -0.62
     ComVisible
    -0.62
    ValueStyle
    -0.62
     tartalomajánló
    -0.62
    GEBURTS
    -0.60
    WebElementEntity
    -0.60
    POSITIVE LOGITS
     JpaRepository
    0.48
     cheek
    0.44
    clf
    0.41
     spit
    0.40
    copo
    0.40
    rlpool
    0.39
    HttpPut
    0.38
     sp
    0.37
     closely
    0.37
    ContentView
    0.37
    Activations Density 1.121%

    No Known Activations