© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2899
    Prev
    Next
    INDEX
    Explanations

    language typical of legal documents and court proceedings.

    oai_token-act-pair · gemini-2.0-flash

    Legal petitions/court cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pet
    -1.99
     Pet
    -1.84
    Pet
    -1.80
    pet
    -1.73
     PET
    -1.70
    PET
    -1.64
     Pets
    -1.48
     pets
    -1.45
    Pets
    -1.42
     Petro
    -1.38
    POSITIVE LOGITS
    enumi
    0.55
     مشين
    0.54
    bootstrapcdn
    0.52
    Datuak
    0.50
    #![
    0.47
    äki
    0.47
    lgari
    0.46
    లాలు
    0.45
    SWR
    0.45
    nault
    0.45
    Activations Density 1.899%

    No Known Activations