© 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. 13652
    Prev
    Next
    INDEX
    Explanations

    parts of a name with the letters "I", "l", "u", "o", or "b"

    oai_token-act-pair · gemini-2.0-flash

    Disjointed text snippets

    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
    mola
    -0.64
    rader
    -0.60
     Lacy
    -0.54
    ximately
    -0.53
    nicity
    -0.53
     BehaviorSubject
    -0.52
     Superhosts
    -0.52
    ladel
    -0.52
    adox
    -0.52
    LabelTagHelper
    -0.52
    POSITIVE LOGITS
     Efq
    0.51
     myö
    0.48
     devriez
    0.47
    CodeAnalysis
    0.47
     Undeclared
    0.47
     paziente
    0.47
     mitä
    0.47
    CrossRef
    0.47
    maked
    0.46
     ettei
    0.46
    Activations Density 0.269%

    No Known Activations