© 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. 10061
    Prev
    Next
    INDEX
    Explanations

    words related to public transportation and city planning, especially bus and streetcar routes, along with numerical identifiers

    oai_token-act-pair · gemini-2.0-flash

    Transportation routes and schedules

    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
    ipedi
    -0.63
     CURIAM
    -0.59
    ųjų
    -0.58
    NUMX
    -0.58
     doGet
    -0.55
    omorph
    -0.54
     LPC
    -0.53
     FetchType
    -0.51
    aliana
    -0.50
    KeySpec
    -0.50
    POSITIVE LOGITS
    RegistryLite
    0.55
     nationaux
    0.55
    webElementXpaths
    0.54
     ideje
    0.52
    Здравствуйте
    0.50
    cheinend
    0.50
     ***!
    0.49
     scheduled
    0.49
     coverage
    0.49
    ppelin
    0.49
    Activations Density 0.578%

    No Known Activations