© 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. 14145
    Prev
    Next
    INDEX
    Explanations

    law journal citations.

    oai_token-act-pair · gemini-2.0-flash

    legal 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
    oa̍t
    -0.85
     stihl
    -0.75
     تضيفلها
    -0.70
     makeStyles
    -0.68
     étr
    -0.67
     AIO
    -0.66
     armé
    -0.66
     Majefty
    -0.66
     doInBackground
    -0.65
     twain
    -0.64
    POSITIVE LOGITS
    ništvo
    0.52
    UPAC
    0.44
    Erreferentziak
    0.43
     front
    0.41
    providedIn
    0.41
     كومونز
    0.40
     ins
    0.40
    íí
    0.40
    WindowConstants
    0.40
     back
    0.39
    Activations Density 3.755%

    No Known Activations