© 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. 6790
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cop" and "lap" or words starting with those letters

    oai_token-act-pair · gemini-2.0-flash

    Art supplies

    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
    reportWebVitals
    -0.69
     secondaires
    -0.55
    Bibliographie
    -0.55
    DotNetBar
    -0.54
    ⓧ
    -0.53
    ConstraintMaker
    -0.53
     jspb
    -0.52
     protoimpl
    -0.51
    readystatechange
    -0.50
    SuppressLint
    -0.48
    POSITIVE LOGITS
    pe
    0.80
    poa
    0.73
    PO
    0.70
    po
    0.70
     PP
    0.68
    pee
    0.66
     PH
    0.66
    pem
    0.65
    pa
    0.65
    pex
    0.65
    Activations Density 0.604%

    No Known Activations