© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 8243
    Prev
    Next
    INDEX
    Explanations

    words in scientific documents that appear to be figure captions or parts of figures and contain mathematical symbols.

    oai_token-act-pair · gemini-2.0-flash

    diverse text patterns or formats

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

    Technical documents

    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
    );*/
    -1.75
    ();*/
    -1.63
    )*/
    -1.59
    }*/
    -1.52
    </blockquote>
    -1.49
     }}$}
    -1.48
    </h5>
    -1.45
    }*/
    
    -1.41
    </h4>
    -1.41
    ;*/
    -1.39
    POSITIVE LOGITS
    ↵↵
    0.74
    bilt
    0.48
     naselje
    0.46
     próprios
    0.45
    Havolalar
    0.43
     sustent
    0.42
    urazione
    0.42
     sendiri
    0.41
     Baillargeon
    0.41
     palm
    0.40
    Activations Density 4.271%

    No Known Activations