© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6085
    Prev
    Next
    INDEX
    Explanations

    the word "mad" or fragments thereof

    oai_token-act-pair · gemini-2.0-flash

    mad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     مشين
    -0.67
    Tracce
    -0.58
    abstractmethod
    -0.57
     intptr
    -0.55
    ContentAsync
    -0.52
     يتيمه
    -0.52
     
    -0.51
     Utility
    -0.48
     vecka
    -0.48
    Bibliograf
    -0.48
    POSITIVE LOGITS
     <=",
    0.72
     متعلقه
    0.65
    TestingModule
    0.55
     >=",
    0.51
    Converting
    0.50
     Alamos
    0.50
    featureID
    0.50
    ptonshire
    0.49
    ($__
    0.49
     samo
    0.49
    Activations Density 0.218%

    No Known Activations