© 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. 5164
    Prev
    Next
    INDEX
    Explanations

    sentences in the form of descriptions or complaints

    oai_token-act-pair · gemini-2.0-flash

    diverse linguistic tokens

    np_token-act-pair-logits · gpt-4o-mini

    foreign 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_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
    ức
    -0.49
    createStatement
    -0.46
     este
    -0.45
    –
    -0.45
    while
    -0.45
     is
    -0.44
     thúc
    -0.44
    hos
    -0.44
     chắc
    -0.43
     while
    -0.43
    POSITIVE LOGITS
     صوتيه
    0.98
     دیکھیے
    0.92
    principalColumn
    0.92
    ArgsConstructor
    0.86
     متعلقه
    0.79
    webElementXpaths
    0.78
     pinulongan
    0.76
     وتسجيلات
    0.76
     nahilalakip
    0.75
     MessageBoxIcon
    0.74
    Activations Density 1.738%

    No Known Activations