© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2908
    Prev
    Next
    INDEX
    Explanations

    mostly, but not exclusively, numeric data with units and percentages, as well as the word "respectively".

    oai_token-act-pair · gemini-2.0-flash

    Uses "respectively"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     respectively
    -2.84
    respectively
    -2.69
     respectivamente
    -2.27
     respective
    -2.17
     respectivement
    -1.75
     соответственно
    -1.68
    respective
    -1.66
     respec
    -1.52
     alike
    -1.35
     respectivos
    -1.34
    POSITIVE LOGITS
    complexContent
    0.65
    httphttps
    0.61
    matchCondition
    0.60
     ModelExpression
    0.60
    GraphicsUnit
    0.59
    nloa
    0.59
    
    0.58
     AssemblyProduct
    0.58
     Administrativna
    0.58
    InjectAttribute
    0.57
    Activations Density 7.163%

    No Known Activations