© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16179
    Prev
    Next
    INDEX
    Explanations

    content from online forums that contains URLs, code snippets, bracketed references, numbered lists, and other formal document structures.

    oai_token-act-pair · gemini-2.0-flash

    internet addresses and code

    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
    ")));
    -0.42
    )";
    -0.39
    ".
    -0.35
    )");
    -0.34
    %");
    -0.34
    bibinfo
    -0.33
     يتيمه
    -0.32
    ."));
    -0.31
    ✨:
    -0.29
    ]";
    -0.29
    POSITIVE LOGITS
     Lign
    0.85
    ּ
    0.83
    ্
    0.83
    ś
    0.83
     Rinse
    0.81
     singoli
    0.80
    qtype
    0.80
    ş
    0.79
    are
    0.79
     élas
    0.79
    Activations Density 21.531%

    No Known Activations