© 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. 4066
    Prev
    Next
    INDEX
    Explanations

    code related to command line utilities and tooling

    oai_token-act-pair · gemini-2.0-flash

    Code and commands

    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
     ostavi
    -0.83
     дописавши
    -0.78
    AccessorTable
    -0.78
    RegistryLite
    -0.71
     ddelweddau
    -0.66
    PreferredItem
    -0.65
    ApiModel
    -0.64
    hasMoreElements
    -0.64
     الرياضيه
    -0.63
    Rujuakan
    -0.62
    POSITIVE LOGITS
    Dest
    0.52
     تانيه
    0.50
    dest
    0.48
     poffible
    0.47
    ųjų
    0.46
     Egli
    0.46
     Dest
    0.46
     dest
    0.45
     méta
    0.45
    mbu
    0.44
    Activations Density 0.850%

    No Known Activations