© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13988
    Prev
    Next
    INDEX
    Explanations

    the word "dig" and its variants

    oai_token-act-pair · gemini-2.0-flash

    dig

    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
    glGen
    -0.60
    onAttach
    -0.54
    getMinutes
    -0.54
    runApp
    -0.50
     CHECKBOX
    -0.50
     SqlDbType
    -0.49
     numberOfRows
    -0.49
     Micros
    -0.49
     onAnimation
    -0.48
    ModelForm
    -0.48
    POSITIVE LOGITS
     تانيه
    0.62
     חיצוניים
    0.59
    itize
    0.58
    ContentAsync
    0.56
     kasarigan
    0.55
    iastes
    0.55
    Aholisi
    0.54
    पया
    0.53
     gynhyrchwyd
    0.53
     gabbana
    0.50
    Activations Density 0.665%

    No Known Activations