© 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. 13849
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "special education".

    oai_token-act-pair · gemini-2.0-flash

    references to special education

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

    special

    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
    execSQL
    -0.67
     dieux
    -0.61
    essional
    -0.54
    ANTON
    -0.54
    IBOutlet
    -0.52
    Citiți
    -0.51
    volved
    -0.49
    nyata
    -0.49
    runApp
    -0.48
     faits
    -0.48
    POSITIVE LOGITS
     needs
    0.63
    )}
    0.62
     NEEDS
    0.56
    )}</
    0.56
     utafitiHapana
    0.56
    needs
    0.55
     للاسماء
    0.54
     Needs
    0.54
    }`).
    0.54
    Needs
    0.53
    Activations Density 2.168%

    No Known Activations