© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 344
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparative analysis and decision-making

    oai_token-act-pair · gemini-2.0-flash

    factor, difference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     vettoriale
    -0.72
    Portail
    -0.68
    Datuak
    -0.64
    Portale
    -0.63
     Circuits
    -0.63
     pagină
    -0.62
     illustrazione
    -0.61
     costante
    -0.60
     Accessories
    -0.60
     semper
    -0.60
    POSITIVE LOGITS
    nonatomic
    0.72
    Przypisy
    0.66
     utafitiHapana
    0.64
     дописавши
    0.52
     tri
    0.51
     Vikipedi
    0.50
    rungsseite
    0.49
    ValueGenerated
    0.49
    ieur
    0.48
     Tri
    0.48
    Activations Density 2.009%

    No Known Activations