© 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. 15906
    Prev
    Next
    INDEX
    Explanations

    Chinese text followed by the phrase "fields are

    oai_token-act-pair · gemini-2.0-flash

    Code errors

    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
    :✨
    -0.78
    MessageTagHelper
    -0.77
    */;
    -0.76
    ⓧ
    -0.74
    ContentAlignment
    -0.69
    */)
    -0.66
    }`).
    -0.65
    $")
    -0.64
     Roskov
    -0.63
    RenderAtEndOf
    -0.62
    POSITIVE LOGITS
     nicio
    0.50
     tightening
    0.45
     anastom
    0.43
     umani
    0.43
     umano
    0.43
    tight
    0.43
     inroads
    0.42
    SOLVED
    0.41
     brink
    0.41
     fijn
    0.41
    Activations Density 0.465%

    No Known Activations