© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3428
    Prev
    Next
    INDEX
    Explanations

    what appears to be a wide variety of information including website code, email addresses, business names, and topics such as slavery and taxes

    oai_token-act-pair · gemini-2.0-flash

    columns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ficulty
    -0.66
    PointerException
    -0.66
    scalatest
    -0.65
    polation
    -0.62
    ieR
    -0.62
    ighbor
    -0.59
    symmetry
    -0.59
    iuo
    -0.59
    etCode
    -0.59
    couvrez
    -0.59
    POSITIVE LOGITS
    out
    0.66
     itſelf
    0.65
    int
    0.61
     Reſ
    0.61
     pleaſure
    0.60
    indi
    0.60
    ſelf
    0.59
    inde
    0.59
    up
    0.59
     poffible
    0.59
    Activations Density 1.179%

    No Known Activations