© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15712
    Prev
    Next
    INDEX
    Explanations

    mathematical notation in Latex

    oai_token-act-pair · gemini-2.0-flash

    mathematical papers

    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
    errHandler
    -0.87
     BoxFit
    -0.84
     myſelf
    -0.76
    omitempty
    -0.73
    mergeFrom
    -0.72
     Jefus
    -0.71
     Monfieur
    -0.71
    ImageContext
    -0.70
     dAtA
    -0.68
     IBOutlet
    -0.66
    POSITIVE LOGITS
     admits
    0.49
     is
    0.48
     admit
    0.48
    Written
    0.47
     lies
    0.45
     live
    0.45
    written
    0.45
     Live
    0.45
     liegen
    0.45
     respects
    0.44
    Activations Density 4.455%

    No Known Activations