© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7154
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and colleges

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    Negative Logits
     propOrder
    -0.79
    ftagPool
    -0.66
    UnknownFieldSet
    -0.66
    UserScript
    -0.64
    sidemargin
    -0.60
     Anci
    -0.56
    AddTagHelper
    -0.56
    epam
    -0.55
     transfieras
    -0.55
     Inspir
    -0.55
    POSITIVE LOGITS
    principalTable
    0.54
    @[+][
    0.52
     متعلقه
    0.52
    basicConfig
    0.50
    NewGuid
    0.50
     soggior
    0.48
    éez
    0.48
    InvalidProtocol
    0.47
    Bioaccumulative
    0.46
    edit
    0.45
    Activations Density 0.321%

    No Known Activations