© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9667
    Prev
    Next
    INDEX
    Explanations

    words that indicate a hierarchical arrangement or system

    oai_token-act-pair · gemini-2.0-flash

    top level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     clínicos
    -0.59
     terapé
    -0.53
    INSEE
    -0.53
    Спо
    -0.50
    下载附件
    -0.48
    必
    -0.47
     pinggang
    -0.47
    testi
    -0.47
    IBAction
    -0.46
    hawatir
    -0.46
    POSITIVE LOGITS
     "..\..\..\
    0.76
    aarrggbb
    0.76
     चीज़ों
    0.74
     raso
    0.73
     "..\..\
    0.71
    ]');
    0.67
     tartalomajánló
    0.67
     ThemeData
    0.66
    }`)
    0.64
    andaş
    0.63
    Activations Density 1.940%

    No Known Activations