© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11083
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with personal computers and computer files, including names of desktop items and software

    oai_token-act-pair · gemini-2.0-flash

    computer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     no
    -0.59
     
    -0.59
     f
    -0.54
     [
    -0.50
     de
    -0.50
     du
    -0.50
     que
    -0.50
     No
    -0.49
     ‘
    -0.49
     ph
    -0.48
    POSITIVE LOGITS
     Jefus
    0.89
     houſe
    0.84
     myſelf
    0.83
     Monfieur
    0.82
     itſelf
    0.82
     fevere
    0.79
     nahilalakip
    0.78
     bedside
    0.77
     pleaſure
    0.77
     neceff
    0.76
    Activations Density 1.633%

    No Known Activations