© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    descriptions of items and where they are stored

    oai_token-act-pair · gemini-2.0-flash

    bags and zippers

    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
    WriteTagHelper
    -0.73
     judiciales
    -0.66
     ujednoznacz
    -0.66
     tiroirs
    -0.63
     &___
    -0.62
     årene
    -0.61
     nationaux
    -0.60
     giudi
    -0.59
     varandra
    -0.59
     réguli
    -0.57
    POSITIVE LOGITS
     }{@
    0.57
    jetas
    0.48
     referenties
    0.46
     pen
    0.46
     arrog
    0.44
    拉斯
    0.44
    mapStateToProps
    0.44
    terday
    0.44
    ostí
    0.44
     đàn
    0.43
    Activations Density 1.445%

    No Known Activations