© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10817
    Prev
    Next
    INDEX
    Explanations

    code-related markup and numbers

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     autorytatywna
    -1.11
    mybatisplus
    -1.08
     nakalista
    -1.05
    AndEndTag
    -1.05
    Tembelea
    -1.02
    UnsafeEnabled
    -1.02
     '\\;'
    -0.96
    XmlAccessType
    -0.94
    
    -0.92
     defaultstate
    -0.91
    POSITIVE LOGITS
    <eos>
    0.45
    ↵
    0.43
    is
    0.42
    $
    0.41
    '
    0.39
    ↵↵
    0.38
    as
    0.37
    f
    0.37
    zen
    0.36
    al
    0.36
    Activations Density 0.311%

    No Known Activations