© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13818
    Prev
    Next
    INDEX
    Explanations

    article formatting elements such as numbers, percentages, and bullet points

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    "):
    -1.10
    '):
    -0.95
    !")
    -0.93
    )";
    -0.93
    ?
    -0.90
     Jefus
    -0.88
    )");
    -0.88
    '},
    -0.88
    .")
    -0.87
    ();
    -0.85
    POSITIVE LOGITS
    .
    0.63
    ​
    0.52
    Read
    0.52
    link
    0.51
     *
    0.50
    лайн
    0.49
    topis
    0.47
    ﾉ
    0.46
     #
    0.46
    éviter
    0.44
    Activations Density 3.000%

    No Known Activations