© 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. 16187
    Prev
    Next
    INDEX
    Explanations

    the word "to" and nearby content.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     féminine
    -0.57
     africaine
    -0.57
     régionale
    -0.57
     dramatique
    -0.55
     gloire
    -0.54
     originali
    -0.54
     littéraire
    -0.54
    Placed
    -0.52
     régional
    -0.52
     étrangère
    -0.52
    POSITIVE LOGITS
     propOrder
    0.74
     mergeFrom
    0.72
    OrBuilder
    0.70
    évaluateur
    0.66
    Koordinaten
    0.63
    Personendaten
    0.61
     congratulate
    0.60
     &___
    0.59
     administer
    0.59
     teach
    0.58
    Activations Density 1.808%

    No Known Activations