© 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. 5381
    Prev
    Next
    INDEX
    Explanations

    code blocks/segments and related keywords such as 'end', '#', 'def', 'private'

    oai_token-act-pair · gemini-2.0-flash

    words with unusual or archaic characters

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

    code and old texts

    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
    ))[
    -0.56
    )))
    
    -0.54
    wirt
    -0.53
     betweenstory
    -0.53
    )]
    
    -0.52
    DockStyle
    -0.52
     standing
    -0.52
    laar
    -0.51
    Koordinaten
    -0.51
    次代
    -0.50
    POSITIVE LOGITS
     pleaſure
    0.80
     houſe
    0.76
     ―――――
    0.72
     Majefty
    0.71
     ſtre
    0.69
     bogotá
    0.68
     Anſ
    0.68
     ſtate
    0.66
     Houſe
    0.65
     itſelf
    0.64
    Activations Density 0.590%

    No Known Activations