© 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. 15246
    Prev
    Next
    INDEX
    Explanations

    CSS color codes (specifically rgba and rgb)

    oai_token-act-pair · gemini-2.0-flash

    Code and markup language

    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
    iettivo
    -0.58
     ujednoznacz
    -0.57
    hasMoreElements
    -0.52
    destroyAll
    -0.52
     overcrow
    -0.51
    IVEREF
    -0.48
    NewReader
    -0.48
     članak
    -0.47
    Xna
    -0.47
    astră
    -0.47
    POSITIVE LOGITS
     >=",
    0.58
     Majefty
    0.57
     }}"></
    0.57
    tagHelper
    0.55
     ]
    0.53
    _
    0.52
    ])->
    0.52
    SourceChecksum
    0.51
     "");
    0.51
    ]}"
    0.50
    Activations Density 0.883%

    No Known Activations