© 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. 14934
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate a past experience

    oai_token-act-pair · gemini-2.0-flash

    forms of "to be"

    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
    awtextra
    -0.50
    PRNewswire
    -0.50
    FetchType
    -0.47
    GOTREF
    -0.44
    GenerationType
    -0.44
    main
    -0.40
    makeConstraints
    -0.39
    Generic
    -0.39
    Based
    -0.38
    based
    -0.37
    POSITIVE LOGITS
    ]--;
    0.82
    joyed
    0.72
     myſelf
    0.69
     uſed
    0.69
     Efq
    0.68
     photolibrary
    0.67
     itſelf
    0.65
     Monfieur
    0.65
    transQ
    0.65
     msec
    0.63
    Activations Density 2.037%

    No Known Activations