© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5688
    Prev
    Next
    INDEX
    Explanations

    The appearance of the word 'net' and related words such as 'recoverable' and 'perhaps'.

    oai_token-act-pair · gemini-2.0-flash

    net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     préfé
    -0.75
    ebus
    -0.69
     Charming
    -0.66
     récente
    -0.64
     taxpayers
    -0.64
     Hugs
    -0.63
     Ohr
    -0.63
     contemporaneous
    -0.63
     taxpayer
    -0.63
     Concurrent
    -0.63
    POSITIVE LOGITS
     يتيمه
    0.77
    таратура
    0.75
    bootstrapcdn
    0.68
    SharedDtor
    0.68
     createSlice
    0.66
     وتسجيلات
    0.66
     isInitialized
    0.66
    存于互联网档案馆
    0.66
     beginnetje
    0.65
    Pautan
    0.65
    Activations Density 2.234%

    No Known Activations