© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5749
    Prev
    Next
    INDEX
    Explanations

    the phrase "quality control"

    oai_token-act-pair · gemini-2.0-flash

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     control
    -1.28
     Control
    -1.10
    Control
    -1.09
    control
    -1.07
    CONTROL
    -0.95
     CONTROL
    -0.93
     Kontrolle
    -0.90
     controls
    -0.90
     controllo
    -0.84
     contrôle
    -0.82
    POSITIVE LOGITS
     nahilalakip
    0.78
     isComment
    0.75
    Personendaten
    0.73
    RuleContext
    0.72
    verwijspagina
    0.68
    AnchorStyles
    0.65
    enderror
    0.65
    styleType
    0.62
    IntoConstraints
    0.62
    SBATCH
    0.62
    Activations Density 0.341%

    No Known Activations