© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10565
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to activities happening or being done

    oai_token-act-pair · gemini-2.0-flash

    everything

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Diweddarwch
    -0.50
    nocześnie
    -0.48
    <bos>
    -0.47
     enten
    -0.46
     >=",
    -0.45
    +:+
    -0.45
    __(/*!
    -0.43
     sumpay
    -0.41
     विश्वसनीयता
    -0.41
     ว่า
    -0.41
    POSITIVE LOGITS
     everything
    3.13
    everything
    2.86
     Everything
    2.77
    Everything
    2.72
     EVERYTHING
    2.17
     tudo
    1.79
     anything
    1.77
     всичко
    1.66
     alles
    1.58
    anything
    1.56
    Activations Density 3.193%

    No Known Activations