© 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. 12782
    Prev
    Next
    INDEX
    Explanations

    square brackets containing numbers

    oai_token-act-pair · gemini-2.0-flash

    1 or period

    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
     <<<<<<<<<<<<<<
    -0.56
    RTRS
    -0.52
    weer
    -0.50
    tiefel
    -0.50
    ).[
    -0.49
    useNewUrlParser
    -0.49
    цездатний
    -0.48
    tagHelperRunner
    -0.48
    ImageContext
    -0.48
     uintptr
    -0.47
    POSITIVE LOGITS
     springfox
    0.64
    Erreferentziak
    0.61
    CodedInputStream
    0.53
    contentLoaded
    0.52
     verticale
    0.52
     stanga
    0.52
    NavController
    0.51
    Demografie
    0.50
     Réponses
    0.50
     Invention
    0.49
    Activations Density 4.789%

    No Known Activations