© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5268
    Prev
    Next
    INDEX
    Explanations

    tokens appearing in the structured format of a scientific paper, along with people moving into neighborhood

    oai_token-act-pair · gemini-2.0-flash

    say proximity

    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
     near
    -2.00
     around
    -1.88
    near
    -1.77
    Near
    -1.73
     Around
    -1.68
    around
    -1.66
     Near
    -1.66
    Around
    -1.64
     NEAR
    -1.43
     AROUND
    -1.43
    POSITIVE LOGITS
     ProtoMessage
    0.51
     TextInputType
    0.45
     roulant
    0.44
    Vit
    0.44
     pinulongan
    0.42
     asistentes
    0.42
     cordes
    0.41
    ScopeManager
    0.41
    aiuto
    0.41
    Diweddarwch
    0.41
    Activations Density 1.339%

    No Known Activations