© 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. 12375
    Prev
    Next
    INDEX
    Explanations

    a mix of somewhat common words that don't really have a clear pattern

    oai_token-act-pair · gemini-2.0-flash

    close

    np_max-act-logits · 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
     ISNI
    -0.58
     referenties
    -0.54
     datter
    -0.50
    retweeted
    -0.49
     uptime
    -0.48
    cartão
    -0.48
     Macromolecules
    -0.48
     gerek
    -0.47
    hazi
    -0.47
    anyon
    -0.46
    POSITIVE LOGITS
     close
    3.56
     Close
    2.91
    close
    2.89
     CLOSE
    2.81
    Close
    2.81
     closer
    2.34
    CLOSE
    2.30
    closer
    2.16
     closest
    2.08
     Closer
    1.94
    Activations Density 10.058%

    No Known Activations