© 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. 3771
    Prev
    Next
    INDEX
    Explanations

    Russian lexicon, related to programming greetings

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
     Monfieur
    -1.09
     bezeichneter
    -0.96
     leçon
    -0.92
     Theſe
    -0.91
     myſelf
    -0.88
    TestingModule
    -0.88
     Efq
    -0.86
     CHAPITRE
    -0.86
     titolata
    -0.85
     auffi
    -0.84
    POSITIVE LOGITS
     
    0.48
     "
    0.46
     as
    0.41
     The
    0.41
     Cor
    0.39
    ↵↵
    0.39
     As
    0.37
     f
    0.37
     El
    0.37
     c
    0.36
    Activations Density 3.222%

    No Known Activations