© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11331
    Prev
    Next
    INDEX
    Explanations

    a mix of technical terms related to diverse fields such as programming, medical procedures, 3D graphics, music production, and geography.

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    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
    nya
    -1.18
    ness
    -1.14
    d
    -0.88
    了
    -0.78
    ly
    -0.77
    に
    -0.77
    nt
    -0.76
    tt
    -0.74
    lle
    -0.70
    lla
    -0.67
    POSITIVE LOGITS
    migrationBuilder
    0.68
    aspectj
    0.54
     كومونز
    0.52
    HttpPut
    0.52
    providedIn
    0.51
    homonymie
    0.50
    TypedDataSet
    0.49
    Xaml
    0.48
    ValueGeneration
    0.48
     légale
    0.47
    Activations Density 3.818%

    No Known Activations