© 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. 12211
    Prev
    Next
    INDEX
    Explanations

    strings of text with the words "alive", "state", or "sight" in them

    oai_token-act-pair · gemini-2.0-flash

    alive

    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
    <bos>
    -0.81
     sight
    -0.65
    sight
    -0.50
     sights
    -0.50
     saites
    -0.49
     angekommen
    -0.48
     ouvertes
    -0.45
     eröff
    -0.45
     citoy
    -0.43
     définiti
    -0.43
    POSITIVE LOGITS
     Roskov
    0.84
    principalColumn
    0.79
     оригіналу
    0.78
     وتسجيلات
    0.72
    astéroïdes
    0.71
    umbersome
    0.69
    expandindo
    0.69
    BagLayout
    0.67
    dart
    0.67
    tanleria
    0.67
    Activations Density 0.458%

    No Known Activations