© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13769
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to law, documents, or estimates.

    oai_token-act-pair · gemini-2.0-flash

    over

    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
     devi
    -0.64
     minim
    -0.63
     dedic
    -0.63
     prioriti
    -0.59
     reconstru
    -0.57
     scra
    -0.57
     aven
    -0.56
    identi
    -0.56
     cra
    -0.56
     til
    -0.55
    POSITIVE LOGITS
     uſe
    1.15
     fhew
    1.09
     ſtand
    0.89
     cauſe
    0.88
     preſent
    0.88
     prefent
    0.83
     themſelves
    0.80
     ſet
    0.79
     defire
    0.79
     erect
    0.77
    Activations Density 25.313%

    No Known Activations