© 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. 12552
    Prev
    Next
    INDEX
    Explanations

    code snippets dealing with the 'files' variable and array indexing, along with loop statements

    oai_token-act-pair · gemini-2.0-flash

    code with files/lists

    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
     at
    -0.48
     encore
    -0.44
    ↵↵
    -0.44
    --
    -0.43
     X
    -0.43
    \
    -0.41
     At
    -0.40
    　
    -0.40
    X
    -0.40
    ्यान
    -0.40
    POSITIVE LOGITS
     Roskov
    1.05
     doInBackground
    0.95
    kháu
    0.93
    Geplaatst
    0.91
    NameInMap
    0.90
    thâu
    0.89
     Efq
    0.88
    VIAF
    0.88
    adpleegd
    0.86
     فريبيس
    0.86
    Activations Density 1.406%

    No Known Activations