© 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. 11045
    Prev
    Next
    INDEX
    Explanations

    words related to standards of product/service and their costs.

    oai_token-act-pair · gemini-2.0-flash

    quality

    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
     quality
    -1.54
    quality
    -1.46
     Quality
    -1.37
    Quality
    -1.35
     QUALITY
    -1.27
    QUALITY
    -1.21
     calidad
    -1.21
     qualidade
    -1.13
     qualité
    -1.10
     kwaliteit
    -1.09
    POSITIVE LOGITS
    ConstraintMaker
    1.05
    CloseOperation
    0.90
     &___
    0.83
     pleaſure
    0.79
    InputBorder
    0.79
    yntaxException
    0.74
     متعلقه
    0.74
    homonymie
    0.71
    complexContent
    0.71
     Majefty
    0.70
    Activations Density 15.532%

    No Known Activations