© 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. 6486
    Prev
    Next
    INDEX
    Explanations

    the word "to" and the words surrounding it

    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
    enderror
    -0.50
     Spiegel
    -0.48
    batore
    -0.47
    minecraftforge
    -0.46
    atti
    -0.45
     Capita
    -0.45
     onOptions
    -0.43
     capital
    -0.43
     tü
    -0.42
     cand
    -0.41
    POSITIVE LOGITS
     help
    1.31
     helping
    1.22
     Help
    1.21
    helping
    1.19
    help
    1.16
    Help
    1.14
     HELP
    1.10
    Helping
    1.09
     Helping
    1.08
    HELP
    1.06
    Activations Density 1.815%

    No Known Activations