© 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. 10171
    Prev
    Next
    INDEX
    Explanations

    technical terms for scientific inventions and procedures

    oai_token-act-pair · gemini-2.0-flash

    science experiments

    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>
    -1.16
     parteci
    -0.54
     gjelder
    -0.53
     चीज़ों
    -0.53
     partecipare
    -0.47
     giardino
    -0.46
     gatto
    -0.45
     
    -0.45
     silenzio
    -0.44
    Obrázky
    -0.44
    POSITIVE LOGITS
    CompleteListener
    0.83
    rungsseite
    0.79
    Билгалдахарш
    0.69
     @{
    0.67
     betweenstory
    0.67
     HasFactory
    0.66
     MUD
    0.64
     verti
    0.63
    BeginContext
    0.62
     ?>/
    0.62
    Activations Density 3.696%

    No Known Activations