© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10086
    Prev
    Next
    INDEX
    Explanations

    the suffixes "lig," "ug," "vig," "proof", and also some Japanese kanji used in programming

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     doGet
    -0.68
     ujednoznacz
    -0.65
     lenker
    -0.63
     تضيفلها
    -0.62
    Lugares
    -0.59
     TestBed
    -0.58
     DialogInterface
    -0.57
     AssemblyTitle
    -0.56
     Factbook
    -0.56
    ArrowToggle
    -0.56
    POSITIVE LOGITS
    λαμβ
    0.48
    وردار
    0.48
     aback
    0.47
    mess
    0.46
    onViewCreated
    0.46
    bedded
    0.45
    jfree
    0.45
     fufficient
    0.45
     Olds
    0.44
    ThemeProvider
    0.43
    Activations Density 1.161%

    No Known Activations