© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2727
    Prev
    Next
    INDEX
    Explanations

    clauses that contain the word "is", "are", "would," "should", "that", or "wish".

    oai_token-act-pair · gemini-2.0-flash

    completely, totally

    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
    Negative Logits
    BagLayout
    -0.60
    varargin
    -0.60
    quelize
    -0.60
     BitmapFactory
    -0.58
    niosek
    -0.54
     vulgaires
    -0.54
    uurs
    -0.53
    TagHelper
    -0.52
     nuages
    -0.52
     désactiv
    -0.52
    POSITIVE LOGITS
     completely
    2.09
     totally
    2.05
     Completely
    1.92
    Completely
    1.88
    totally
    1.86
     entirely
    1.84
    completely
    1.84
     Totally
    1.77
    Totally
    1.73
     completamente
    1.63
    Activations Density 4.771%

    No Known Activations