© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4723
    Prev
    Next
    INDEX
    Explanations

    the word "what"

    oai_token-act-pair · gemini-2.0-flash

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AutoScaleMode
    -0.77
    UnusedPrivate
    -0.74
    interopRequire
    -0.73
    
    -0.69
     disponibilités
    -0.60
     متعلقه
    -0.60
     indietro
    -0.59
    లాలు
    -0.59
    дыду
    -0.58
    FormTagHelper
    -0.57
    POSITIVE LOGITS
     kind
    0.57
    heri
    0.57
     sort
    0.52
    AddTagHelper
    0.52
    hner
    0.50
    hev
    0.49
    DateFormat
    0.48
    ipu
    0.46
     type
    0.46
     espécie
    0.46
    Activations Density 0.277%

    No Known Activations