© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15307
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" and "that," sometimes in conjunction with other words

    oai_token-act-pair · gemini-2.0-flash

    this or that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     AssemblyCompany
    -0.69
    الحياه
    -0.68
     صوتيه
    -0.65
     समीक्षाएं
    -0.63
    ContentAlignment
    -0.62
    imageshack
    -0.58
    EndContext
    -0.58
    HostException
    -0.58
     propOrder
    -0.57
    SpringBootTest
    -0.57
    POSITIVE LOGITS
    dymyr
    0.51
     препратки
    0.46
    ərbaycan
    0.42
    اعده
    0.42
    koin
    0.42
    nosaurus
    0.40
    blem
    0.40
    Siddhartha
    0.39
    missão
    0.39
    گزاری
    0.39
    Activations Density 0.483%

    No Known Activations