© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12292
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    зумі
    -0.56
     링크
    -0.56
    cagon
    -0.52
     урна
    -0.51
    feit
    -0.50
    gulama
    -0.49
     desglose
    -0.48
    rdı
    -0.48
    ictured
    -0.47
    曖昧さ回避
    -0.46
    POSITIVE LOGITS
    expandindo
    0.62
    protoimpl
    0.60
    ########.
    0.59
    ญ
    0.53
    ])))
    0.52
     resourceCulture
    0.51
    }">
    0.48
     UVB
    0.48
     OFDb
    0.48
     PicClick
    0.48
    Activations Density 11.919%

    No Known Activations