© 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. 16046
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate contrasting ideas and comparisons

    oai_token-act-pair · 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
     peindre
    -1.04
     uſe
    -0.85
    seamnă
    -0.82
     défendre
    -0.81
     faſt
    -0.80
     boire
    -0.79
     uſed
    -0.78
     iſt
    -0.77
     itſelf
    -0.77
     Utilisez
    -0.76
    POSITIVE LOGITS
     li
    0.55
     pun
    0.53
    lifer
    0.53
     le
    0.48
     sp
    0.47
    hlander
    0.47
     l
    0.46
     ri
    0.46
    barer
    0.46
     studier
    0.46
    Activations Density 2.160%

    No Known Activations