© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3532
    Prev
    Next
    INDEX
    Explanations

    references to land, geography, and trails

    oai_token-act-pair · gemini-2.0-flash

    directions and location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    CodedInputStream
    -0.71
     getchar
    -0.61
    FontOfSize
    -0.60
    styleType
    -0.60
    invokeLater
    -0.56
    GraphicsUnit
    -0.54
     SBP
    -0.54
     flint
    -0.53
     Kyu
    -0.53
     Roskov
    -0.52
    POSITIVE LOGITS
    __':
    0.62
    rungsseite
    0.56
    __":
    0.52
     termica
    0.49
    \{\\
    0.49
    hfill
    0.47
     provisoire
    0.46
    typeorm
    0.45
    TestingModule
    0.45
    sizeCache
    0.44
    Activations Density 4.773%

    No Known Activations