© 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. 3261
    Prev
    Next
    INDEX
    Explanations

    action words that indicate experimentation and statistical significance

    oai_token-act-pair · gemini-2.0-flash

    Scientific studies

    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
    momix
    -0.53
    ]--;
    -0.46
     Phaser
    -0.45
    chnen
    -0.44
    ."));
    -0.44
    .";
    
    -0.44
     Xunit
    -0.43
    WebElementEntity
    -0.43
    ''')
    -0.43
     ""));
    -0.43
    POSITIVE LOGITS
    BoxShadow
    0.66
     allAfrica
    0.60
     Normdatei
    0.60
     fubject
    0.58
     JpaRepository
    0.58
     चीज़ों
    0.56
     MainAxisSize
    0.56
    PRNewswire
    0.53
    IBOutlet
    0.52
     cauza
    0.50
    Activations Density 9.848%

    No Known Activations