© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10865
    Prev
    Next
    INDEX
    Explanations

    text involving a tank changing direction

    oai_token-act-pair · gemini-2.0-flash

    left and right

    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
     onCancelled
    -0.57
    ্ন
    -0.56
    ApiOperation
    -0.54
     EconPapers
    -0.52
    ༘
    -0.50
     heureux
    -0.49
    metro
    -0.48
     STAM
    -0.46
     lavanda
    -0.46
    assertNot
    -0.46
    POSITIVE LOGITS
     left
    2.05
     Left
    1.74
    left
    1.69
    Left
    1.67
     LEFT
    1.61
    LEFT
    1.44
     right
    1.32
    左
    1.32
     Right
    1.31
     lef
    1.30
    Activations Density 5.223%

    No Known Activations