© 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. 6152
    Prev
    Next
    INDEX
    Explanations

    character pairings like "7 1" and "2 9"

    oai_token-act-pair · gemini-2.0-flash

    code/references

    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
     fifth
    -1.05
    Fifth
    -0.96
     Fifth
    -0.96
     FIVE
    -0.91
     five
    -0.91
    fifth
    -0.91
     FIFTH
    -0.90
     Five
    -0.89
    FIVE
    -0.86
    五
    -0.85
    POSITIVE LOGITS
    dataTables
    0.45
     Wund
    0.43
     portes
    0.42
    WindowConstants
    0.42
    Handles
    0.40
     Baillargeon
    0.40
    RECEIVE
    0.39
     adatt
    0.39
     حقوق
    0.39
    crí
    0.38
    Activations Density 1.124%

    No Known Activations