© 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. 16341
    Prev
    Next
    INDEX
    Explanations

    text describing a sports game or season

    oai_token-act-pair · gemini-2.0-flash

    series

    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
     planche
    -0.55
     säker
    -0.52
    EDEFAULT
    -0.52
    щер
    -0.49
    tableFuture
    -0.48
    ορ
    -0.45
    ">//
    -0.45
     mourut
    -0.44
     нара
    -0.44
     geme
    -0.43
    POSITIVE LOGITS
     showing
    0.93
     stretch
    0.87
     run
    0.83
     Showing
    0.82
    showing
    0.81
     spell
    0.76
    Autoritní
    0.73
    Showing
    0.72
     SHOWING
    0.71
     Stretch
    0.67
    Activations Density 1.478%

    No Known Activations