© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4355
    Prev
    Next
    INDEX
    Explanations

    articles followed by words imparting additional information

    oai_token-act-pair · gemini-2.0-flash

    Subjective judgments

    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
     AttributeSet
    -0.61
    FTFY
    -0.56
    toggler
    -0.54
     DBNull
    -0.54
    ⋙
    -0.52
     оригіналу
    -0.51
     fossa
    -0.49
    CodeAttribute
    -0.49
    avut
    -0.48
    TextFormField
    -0.47
    POSITIVE LOGITS
     measure
    0.82
    measure
    0.77
     touch
    0.77
     air
    0.75
    Measure
    0.69
     Measure
    0.66
     element
    0.65
    tanleria
    0.65
     degree
    0.64
    air
    0.61
    Activations Density 1.450%

    No Known Activations