© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11427
    Prev
    Next
    INDEX
    Explanations

    code snippets in a variety of programming languages with punctuation and math symbols in the mix.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    TargetApi
    -0.54
    ubio
    -0.52
    EnableWeb
    -0.47
    rig
    -0.45
     lemn
    -0.44
    alyptus
    -0.43
    ONTO
    -0.42
    ;#
    -0.42
    ponto
    -0.42
    #
    -0.41
    POSITIVE LOGITS
     EconPapers
    0.63
    }`).
    0.63
    )}</
    0.63
     Roskov
    0.62
    !")
    0.59
     esternos
    0.59
    })*/
    0.58
    ostante
    0.57
    MemoryWarning
    0.57
    %]
    0.57
    Activations Density 1.147%

    No Known Activations