© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9786
    Prev
    Next
    INDEX
    Explanations

    code snippets involving Java or similar languages, including keywords like "public," "class," "return," and file extensions.

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Efq
    -1.05
     itſelf
    -1.02
     myſelf
    -1.01
     Jefus
    -0.99
     Monfieur
    -0.90
     raiſ
    -0.90
     pleaſure
    -0.85
     houſe
    -0.81
     Theſe
    -0.79
     themſelves
    -0.79
    POSITIVE LOGITS
    ’
    0.71
    ,'
    0.70
    ',
    0.69
    '
    0.69
    '.
    0.69
     es
    0.68
    ’.
    0.67
    .'
    0.66
     di
    0.65
    ,"
    0.65
    Activations Density 16.101%

    No Known Activations