© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to time and events

    oai_token-act-pair · 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
     Ty
    -0.55
    ,
    -0.52
    gtest
    -0.51
    anyahu
    -0.48
     pr
    -0.48
     mergeFrom
    -0.46
    formik
    -0.46
     tw
    -0.46
    Ty
    -0.45
    copal
    -0.44
    POSITIVE LOGITS
    Rhestr
    0.69
     supérieurs
    0.62
     kvinder
    0.61
     esterni
    0.60
     étoit
    0.60
     feroit
    0.59
     normaux
    0.59
     réguli
    0.59
     vapeur
    0.59
     defaultstate
    0.57
    Activations Density 2.520%

    No Known Activations