© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15675
    Prev
    Next
    INDEX
    Explanations

    the word "this"

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     fikir
    -0.51
    AndEndTag
    -0.50
     препратки
    -0.49
    :✨
    -0.49
     rather
    -0.46
     اجرای
    -0.44
     which
    -0.44
    PrototypeOf
    -0.43
     gawas
    -0.43
     maîtres
    -0.43
    POSITIVE LOGITS
     Roskov
    0.73
    ]));
    0.67
    )];
    0.63
    Filmographie
    0.62
     ComVisible
    0.62
    ]),
    0.62
    UnusedPrivate
    0.61
    =$?
    0.61
     DbContext
    0.60
    }\]
    0.60
    Activations Density 0.317%

    No Known Activations