© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9733
    Prev
    Next
    INDEX
    Explanations

    the letter "g" preceded by certain other letters.

    oai_token-act-pair · gemini-2.0-flash

    uncommon words

    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
    UnsafeEnabled
    -0.78
    לין
    -0.70
    +:+
    -0.68
    RectangleBorder
    -0.68
     AspNetCore
    -0.64
    CodeAttribute
    -0.63
    tanleria
    -0.63
    IsMutable
    -0.61
    !*\
    -0.60
    straw
    -0.60
    POSITIVE LOGITS
     mourut
    0.46
    heden
    0.43
     revés
    0.41
    #
    0.41
    ضور
    0.39
     vœux
    0.38
     télécharge
    0.38
    NSNumber
    0.38
     femininos
    0.37
    ultu
    0.37
    Activations Density 0.811%

    No Known Activations