© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11777
    Prev
    Next
    INDEX
    Explanations

    lines made of hyphens

    oai_token-act-pair · gemini-2.0-flash

    non-standard or stylized text elements

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

    ----------------

    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
     val
    -0.54
     “
    -0.49
     (
    -0.49
     «
    -0.49
     
    -0.47
     ‘
    -0.47
     O
    -0.47
     o
    -0.46
      
    -0.46
     "
    -0.46
    POSITIVE LOGITS
    rungsseite
    1.04
     myſelf
    0.97
     Theſe
    0.92
     becauſe
    0.88
     photolibrary
    0.88
     ―――――
    0.87
     itſelf
    0.87
     Houſe
    0.85
     pleaſure
    0.84
     Diſ
    0.84
    Activations Density 0.669%

    No Known Activations