© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3799
    Prev
    Next
    INDEX
    Explanations

    context words within conversational text, potentially song lyrics or casual dialogue

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or non-standard encodings

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

    Sentence beginnings

    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
     
    -0.96
    2
    -0.85
    1
    -0.85
     (
    -0.84
    ,
    -0.82
    ↵↵
    -0.82
    3
    -0.81
    .
    -0.78
    5
    -0.77
    ↵
    -0.76
    POSITIVE LOGITS
     Theſe
    1.48
     ویکی‌آمباردا
    1.35
    expandindo
    1.34
     itſelf
    1.33
     Мексичка
    1.32
    posedge
    1.30
     bezeichneter
    1.24
     myſelf
    1.23
    AndEndTag
    1.20
    __':
    1.19
    Activations Density 19.942%

    No Known Activations