© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    android XML code

    oai_token-act-pair · gemini-2.0-flash

    Android code snippets

    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
     pri
    -0.55
     .
    -0.55
     term
    -0.51
     Home
    -0.51
     pre
    -0.51
     ,
    -0.49
    inan
    -0.49
     West
    -0.48
     fast
    -0.48
     parts
    -0.48
    POSITIVE LOGITS
    featureID
    0.97
     nahilalakip
    0.73
    цездатний
    0.70
    XMLSchema
    0.69
    GEBURTSDATUM
    0.67
    LookAnd
    0.65
     propOrder
    0.65
    NUMX
    0.64
    ViewFeatures
    0.61
     snippetHide
    0.61
    Activations Density 1.770%

    No Known Activations