© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10013
    Prev
    Next
    INDEX
    Explanations

    words and phrases common in legal writing

    oai_token-act-pair · gemini-2.0-flash

    a/an

    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
    tonsoft
    -0.59
     any
    -0.52
    AddHtmlAttribute
    -0.49
     defaultstate
    -0.48
     R
    -0.47
    expandindo
    -0.44
     a
    -0.43
    djangoproject
    -0.42
     begy
    -0.41
     bids
    -0.41
    POSITIVE LOGITS
     himſelf
    0.77
     myſelf
    0.74
     itſelf
    0.70
     Diſ
    0.64
     themſelves
    0.61
     Anſ
    0.59
     ISNI
    0.59
    #+#
    0.58
    enumi
    0.58
     Reſ
    0.57
    Activations Density 3.617%

    No Known Activations