© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13184
    Prev
    Next
    INDEX
    Explanations

    the word "evaluation" or "evaluated"

    oai_token-act-pair · gemini-2.0-flash

    evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     evaluation
    -2.23
     Evaluation
    -2.05
     evaluate
    -1.98
    Evaluation
    -1.98
     evaluated
    -1.95
    evaluation
    -1.85
     evaluations
    -1.85
     evaluating
    -1.84
     EVALUATION
    -1.77
     Evaluate
    -1.73
    POSITIVE LOGITS
    ệc
    0.65
    antaranya
    0.65
     виправивши
    0.64
     ")");
    0.61
    %")
    0.60
    ष्य
    0.60
    %");
    0.59
    __))
    0.57
    Filmographie
    0.57
    ichteten
    0.57
    Activations Density 0.377%

    No Known Activations