© 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. 16072
    Prev
    Next
    INDEX
    Explanations

    words related to configuration files and settings

    oai_token-act-pair · gemini-2.0-flash

    config

    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
     betweenstory
    -0.62
    adpleegd
    -0.57
    principalTable
    -0.54
    istoitu
    -0.54
     OFDb
    -0.53
     Roskov
    -0.52
    SocketChannel
    -0.51
    empereur
    -0.50
    oa̍t
    -0.50
    withIdentifier
    -0.49
    POSITIVE LOGITS
     שוליים
    0.61
    #
    0.57
    ArgumentParser
    0.52
    CppMethod
    0.51
     Fairmont
    0.50
     szóci
    0.50
    ItemGroup
    0.49
     übersch
    0.49
    nadier
    0.48
    filepath
    0.48
    Activations Density 1.186%

    No Known Activations