© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7840
    Prev
    Next
    INDEX
    Explanations

    the word "waste" and related terms, sometimes in the context of resource consumption or undesirable situations

    oai_token-act-pair · gemini-2.0-flash

    waste and talk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     désolés
    -0.53
     AssemblyCompany
    -0.51
    GraphicsUnit
    -0.50
    ValueGenerated
    -0.50
     INTERESAR
    -0.50
    yargs
    -0.49
     referenties
    -0.49
     pulumi
    -0.48
    iería
    -0.48
    HandleFunc
    -0.46
    POSITIVE LOGITS
    walk
    0.55
    WALK
    0.53
    ThroughAttribute
    0.52
    tegra
    0.50
     eun
    0.49
    tableFuture
    0.49
     Paglinawan
    0.48
    pium
    0.48
    oredCriteria
    0.47
     Amad
    0.46
    Activations Density 0.778%

    No Known Activations