© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4169
    Prev
    Next
    INDEX
    Explanations

    car or engine types designated as V8, V6, GLK350, GLK320 or 383

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     latest
    -0.47
     Zacks
    -0.46
     various
    -0.45
    tisti
    -0.42
     recent
    -0.41
     former
    -0.41
    Latest
    -0.41
     ModelExpression
    -0.40
     yakin
    -0.40
    tagHelper
    -0.40
    POSITIVE LOGITS
     Normdatei
    0.83
     Wikimedijinoj
    0.82
    InjectAttribute
    0.81
    TintMode
    0.77
     الدولى
    0.73
    InstrumentedTest
    0.73
    EndContext
    0.72
    Демографія
    0.71
    lapsingToolbar
    0.69
     فريبيس
    0.68
    Activations Density 0.695%

    No Known Activations