© 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. 10912
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to efficiency, effectiveness, and process improvement.

    oai_token-act-pair · gemini-2.0-flash

    efficient

    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
     effectiveness
    -1.02
     efficiency
    -0.96
     effective
    -0.93
     efficacité
    -0.90
     Effectiveness
    -0.88
    efficacité
    -0.87
     effic
    -0.87
     efficient
    -0.86
    效率
    -0.85
     effici
    -0.85
    POSITIVE LOGITS
     لينك
    0.72
     wireType
    0.65
    merie
    0.63
    +:+
    0.63
    よいよ
    0.62
    
    0.61
     sumpay
    0.60
    Parcelize
    0.59
    Abitanti
    0.58
     '\\;'
    0.58
    Activations Density 22.997%

    No Known Activations