© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7390
    Prev
    Next
    INDEX
    Explanations

    sentences describing transformative changes, particularly those ending in "ize" or containing "role," "affect," or "play."

    oai_token-act-pair · gemini-2.0-flash

    ize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     تضيفلها
    -0.84
     оригіналу
    -0.84
     initComponents
    -0.83
     TextInputType
    -0.73
     HasFactory
    -0.72
    ScopeManager
    -0.71
     RIPRODUZIONE
    -0.71
    kloped
    -0.69
     referrerpolicy
    -0.67
    tagext
    -0.67
    POSITIVE LOGITS
    <bos>
    0.82
    '
    0.54
     helpen
    0.50
    ..
    0.49
     helping
    0.48
     i
    0.47
     promise
    0.45
     Pro
    0.45
    ja
    0.45
    della
    0.44
    Activations Density 1.871%

    No Known Activations