© 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. 6270
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "you", especially when followed by "can" or "will"

    oai_token-act-pair · gemini-2.0-flash

    you

    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
     pinulongan
    -0.58
    ::_('
    -0.52
     muualla
    -0.51
     exteriores
    -0.50
     виправивши
    -0.50
     esternos
    -0.49
    abetes
    -0.49
     Zwer
    -0.49
    hadas
    -0.48
    roveň
    -0.48
    POSITIVE LOGITS
    EndProject
    0.52
    GEBURTSDATUM
    0.52
     otomatig
    0.49
     gynnwys
    0.48
     jLabel
    0.47
     Loop
    0.47
     initComponents
    0.45
    Bibliograf
    0.45
     appui
    0.44
     loop
    0.44
    Activations Density 3.466%

    No Known Activations