© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5168
    Prev
    Next
    INDEX
    Explanations

    conditional situations and potential problems

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Something
    -2.09
     Something
    -2.09
     something
    -1.98
    something
    -1.97
     SOMETHING
    -1.47
    Someone
    -1.38
     Someone
    -1.35
     qualcosa
    -1.35
     algo
    -1.29
     quelque
    -1.27
    POSITIVE LOGITS
     NSCoder
    0.77
    Geplaatst
    0.71
    contentLoaded
    0.71
    PrototypeOf
    0.70
    FormTagHelper
    0.67
     &___
    0.63
    Parcelize
    0.63
    SharedDtor
    0.62
    stateProvider
    0.59
     ExecuteAsync
    0.59
    Activations Density 11.730%

    No Known Activations