© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9287
    Prev
    Next
    INDEX
    Explanations

    the word "the" and the words near it, sometimes assigning activation to other nearby words in the sentence.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    fjspx
    -0.70
    ]='\
    -0.69
     تانيه
    -0.63
    =$?
    -0.63
     }}"></
    -0.61
     Audiodateien
    -0.60
    webElementGuid
    -0.58
    )");
    -0.57
     Preguntas
    -0.57
    ]--;
    -0.55
    POSITIVE LOGITS
     situation
    1.03
    situation
    0.89
     affair
    0.81
     program
    0.75
     event
    0.74
     project
    0.73
     phenomenon
    0.73
     system
    0.73
     matter
    0.72
     scheme
    0.71
    Activations Density 2.629%

    No Known Activations