© 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. 12935
    Prev
    Next
    INDEX
    Explanations

    words related to paperwork, documentation, military, legal proceedings, and research studies

    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
     &
    -1.02
    and
    -0.94
    &
    -0.91
     or
    -0.86
     +
    -0.85
    /
    -0.85
     and
    -0.84
    +
    -0.82
     /
    -0.81
     plus
    -0.77
    POSITIVE LOGITS
     myſelf
    1.52
    ^(@)
    1.41
    ſelves
    1.34
     itſelf
    1.32
     Efq
    1.31
    ſelf
    1.28
    RectangleBorder
    1.27
     doubtnut
    1.25
    DoubleQuotes
    1.24
     purpoſe
    1.24
    Activations Density 9.642%

    No Known Activations