© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    code-related keywords (C, char, string, UTF, main, include)

    oai_token-act-pair · gemini-2.0-flash

    char

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    rungsseite
    -1.02
    findpost
    -0.78
    TestingModule
    -0.66
    SharedCtor
    -0.66
     विश्वसनीयता
    -0.57
    ScopeManager
    -0.57
    Jereo
    -0.55
    -------------</
    -0.54
     Numerade
    -0.52
    المكان
    -0.52
    POSITIVE LOGITS
    lblNewLabel
    0.60
    extAlignment
    0.58
    posedge
    0.52
     AssemblyCulture
    0.51
    CppCodeGen
    0.49
     étanche
    0.48
    resizingMask
    0.48
    зайн
    0.47
    udahkan
    0.47
    quester
    0.47
    Activations Density 1.551%

    No Known Activations