© 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. 11638
    Prev
    Next
    INDEX
    Explanations

    code snippets and text strings related to SMS messages, Facebook, and potentially other social network APIs

    oai_token-act-pair · gemini-2.0-flash

    words with specific suffix patterns

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

    Code and foreign languages

    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
     pinulongan
    -0.75
     AppCompatTheme
    -0.75
    Demografia
    -0.71
    __*/
    -0.69
     الحره
    -0.66
    RenderAtEndOf
    -0.66
     NSCoder
    -0.65
     يتيمه
    -0.64
    HasForeignKey
    -0.59
    aarrggbb
    -0.59
    POSITIVE LOGITS
    ًا
    0.83
    اً
    0.72
    ا
    0.70
    ми
    0.69
    mi
    0.60
    ami
    0.59
    МИ
    0.56
    jem
    0.55
    em
    0.54
    tami
    0.53
    Activations Density 0.530%

    No Known Activations