© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5414
    Prev
    Next
    INDEX
    Explanations

    code in languages related to processing and servers, possibly in C++

    oai_token-act-pair · gemini-2.0-flash

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    "):
    -2.20
    )");
    -2.17
    ")));
    -2.14
    '):
    -2.09
    "])
    -2.02
    >");
    -2.02
    '},
    -2.00
    "));
    -1.97
    !")
    -1.96
    "),
    -1.95
    POSITIVE LOGITS
    ↵
    1.30
    .
    1.19
     and
    1.05
    ↵↵
    1.05
    (
    1.02
    ,
    1.01
     (
    0.90
      
    0.79
    -
    0.77
    1
    0.70
    Activations Density 1.446%

    No Known Activations