© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10459
    Prev
    Next
    INDEX
    Explanations

    words indicating an action or finding was published in a paper or other document

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to discussions and descriptions

    np_token-act-pair-logits · gpt-4o-mini

    Referring to previous text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    httphttps
    -0.50
    żeli
    -0.49
     của
    -0.47
    kegaard
    -0.46
     ahol
    -0.45
     ζωή
    -0.44
    orek
    -0.43
    GHIJKLM
    -0.43
     Pilate
    -0.43
    ของ
    -0.43
    POSITIVE LOGITS
    Rohy
    0.79
    WarningLevel
    0.63
    tonsoft
    0.63
    TargetException
    0.63
     InputDecoration
    0.60
    CodedInputStream
    0.59
     समीक्षक
    0.57
    arschu
    0.57
     kasarigan
    0.57
     AssemblyProduct
    0.57
    Activations Density 5.208%

    No Known Activations