© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4110
    Prev
    Next
    INDEX
    Explanations

    terms and verbs related to legal procedures and reports

    oai_token-act-pair · gemini-2.0-flash

    recommendation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    fileID
    -0.53
    blockList
    -0.50
    RX
    -0.47
     PMA
    -0.47
    rx
    -0.46
     surface
    -0.45
    éenne
    -0.45
    いま
    -0.45
     Langue
    -0.44
     RX
    -0.44
    POSITIVE LOGITS
    íslu
    0.82
    verwijspagina
    0.73
    sizeCache
    0.69
    WriteBarrier
    0.68
    GEBURTSDATUM
    0.67
     AppComponent
    0.64
    IsPostBack
    0.61
    strix
    0.61
    memcmp
    0.60
     Scy
    0.60
    Activations Density 1.309%

    No Known Activations