© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11739
    Prev
    Next
    INDEX
    Explanations

    a mix of Indonesian words and certain English pronouns and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or annotations

    np_token-act-pair-logits · gpt-4o-mini
    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
     solcher
    -0.54
     فريبيس
    -0.54
     arşivlendi
    -0.53
    utnik
    -0.51
    nsis
    -0.51
     通販
    -0.47
    orsese
    -0.47
    %?
    -0.46
    avaş
    -0.46
     gelukkig
    -0.46
    POSITIVE LOGITS
     Wikimedijinoj
    0.64
    fxml
    0.57
     treating
    0.53
     endwhile
    0.51
    Viited
    0.51
    unmodifiable
    0.49
    gemeente
    0.49
     declaring
    0.49
     lateinit
    0.49
    DeleteMapping
    0.48
    Activations Density 0.137%

    No Known Activations