© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8984
    Prev
    Next
    INDEX
    Explanations

    words related to women, children, and schools, especially in the context of education

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'study'

    np_token-act-pair-logits · gpt-4o-mini

    study

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     teaching
    -1.16
    teaching
    -1.03
     Teaching
    -1.03
    Teaching
    -0.98
     TEACH
    -0.96
     teach
    -0.96
     Teach
    -0.95
     TEACHING
    -0.94
    TEACH
    -0.91
     teacher
    -0.89
    POSITIVE LOGITS
     study
    1.00
    study
    0.86
    Study
    0.85
     Study
    0.84
     studied
    0.84
    +#+#
    0.79
    studied
    0.77
     STUDY
    0.77
    STUDY
    0.77
     studying
    0.75
    Activations Density 1.465%

    No Known Activations