© 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. 6583
    Prev
    Next
    INDEX
    Explanations

    disclaimers related to privacy and external websites

    oai_token-act-pair · gemini-2.0-flash

    Legal disclaimers

    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
     propOrder
    -0.76
     تضيفلها
    -0.75
    expandindo
    -0.74
    AddTagHelper
    -0.73
    ruptedException
    -0.71
    DockStyle
    -0.69
    principalTable
    -0.66
    NOPQRST
    -0.65
     Throwable
    -0.64
    errar
    -0.64
    POSITIVE LOGITS
     zucca
    0.45
    往
    0.41
    ipts
    0.37
    úly
    0.37
    thers
    0.36
    ypeł
    0.36
    imah
    0.36
    grafías
    0.36
    ogy
    0.35
     Allein
    0.35
    Activations Density 7.114%

    No Known Activations