© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2715
    Prev
    Next
    INDEX
    Explanations

    words with positive connotations that describe outcomes, experimental design or scientific processes, including the word effective with very high weight

    oai_token-act-pair · gemini-2.0-flash

    effective/efficient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     effective
    -1.13
     Effective
    -1.13
    Effective
    -1.06
     EFFECTIVE
    -1.05
    effective
    -1.05
     Efficient
    -1.02
     efficacité
    -0.97
     Effectiveness
    -0.96
     efficace
    -0.96
     efficient
    -0.96
    POSITIVE LOGITS
    ]));
    0.49
     ");
    0.48
     re
    0.48
    )));
    0.48
    "];
    0.47
    );
    0.46
    ]]
    0.46
    애
    0.45
    ));
    0.45
     bu
    0.45
    Activations Density 18.691%

    No Known Activations