© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    mentions of astronomical events, their discovery, or disease symptoms

    oai_token-act-pair · gemini-2.0-flash

    new things appearing

    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
    BeginContext
    -0.67
    multicolumn
    -0.64
    起的
    -0.61
     JADX
    -0.59
    RenderAtEndOf
    -0.58
     referenties
    -0.56
    ódó
    -0.52
    ViewFeatures
    -0.51
    起
    -0.50
     références
    -0.49
    POSITIVE LOGITS
    +#+
    0.57
    TintMode
    0.54
     moteur
    0.53
    erals
    0.51
    bsp
    0.50
     motores
    0.49
     Matériau
    0.49
    sapp
    0.48
    Enllaces
    0.48
    ICHT
    0.48
    Activations Density 1.894%

    No Known Activations