© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12763
    Prev
    Next
    INDEX
    Explanations

    capitalized words or phrases in financial, legal, medical, and political documents

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    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
     their
    -0.68
     his
    -0.66
     your
    -0.64
     thy
    -0.60
     they
    -0.59
     our
    -0.59
     its
    -0.59
     whereof
    -0.57
     maintenance
    -0.56
     yours
    -0.56
    POSITIVE LOGITS
     stället
    0.78
     cœurs
    0.67
     cérami
    0.67
     lèvres
    0.67
     genoux
    0.63
     ProtoMessage
    0.62
     kaarangay
    0.60
     tiroirs
    0.60
     épaules
    0.59
     jambes
    0.57
    Activations Density 3.489%

    No Known Activations