© 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. 11176
    Prev
    Next
    INDEX
    Explanations

    phrases describing events and situations

    oai_token-act-pair · gemini-2.0-flash

    happen

    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
     Efq
    -1.27
     fhew
    -1.10
     myſelf
    -1.05
     crdi
    -1.01
    ^(@)
    -1.00
     iſt
    -0.97
     doubtnut
    -0.94
     Anſ
    -0.94
     Theſe
    -0.93
     itſelf
    -0.91
    POSITIVE LOGITS
     recently
    0.58
     on
    0.58
     to
    0.57
     after
    0.55
     for
    0.55
     in
    0.54
     easily
    0.53
     with
    0.52
     inside
    0.52
    .
    0.51
    Activations Density 13.767%

    No Known Activations