© 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. 2917
    Prev
    Next
    INDEX
    Explanations

    contractions of "I will" or "I have"

    oai_token-act-pair · gemini-2.0-flash

    ll

    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
    WriteTagHelper
    -0.57
    makeConstraints
    -0.48
    IntoConstraints
    -0.46
    Qui
    -0.44
     Qui
    -0.43
    elsa
    -0.42
    IM
    -0.41
    erover
    -0.41
     slik
    -0.41
    ili
    -0.40
    POSITIVE LOGITS
    ніципа
    0.70
    ValueStyle
    0.66
     Sabina
    0.64
    íncia
    0.62
    Bioaccumulative
    0.60
    AutoScaleMode
    0.60
     getPost
    0.59
    afficheront
    0.59
     pcx
    0.57
     Seis
    0.57
    Activations Density 1.100%

    No Known Activations