© 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. 4635
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming terms and health related items

    oai_token-act-pair · gemini-2.0-flash

    "cases" in code/health

    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
    ArgsConstructor
    -0.81
    ChildScrollView
    -0.70
    elemField
    -0.67
    DebuggerStep
    -0.66
    ⓧ
    -0.63
     mergeFrom
    -0.60
    MemoryWarning
    -0.60
    MockBean
    -0.58
    terdam
    -0.57
    IUrlHelper
    -0.56
    POSITIVE LOGITS
    migrationBuilder
    0.50
    SOUNDBITE
    0.47
     iprot
    0.44
    piram
    0.42
    ricanes
    0.41
    omores
    0.41
    Pfalz
    0.41
     matric
    0.40
    éez
    0.39
     normalement
    0.39
    Activations Density 9.132%

    No Known Activations