© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13591
    Prev
    Next
    INDEX
    Explanations

    source code, commands, and file paths

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Nationalité
    -0.52
    AlterField
    -0.47
    évaluateur
    -0.46
    kra
    -0.45
     microfiber
    -0.44
    Diwedd
    -0.44
     ActivatedRoute
    -0.44
    RepeatedField
    -0.43
     Finch
    -0.43
    PerPage
    -0.43
    POSITIVE LOGITS
    ")));
    0.65
    //</
    0.57
     utafitiHapana
    0.57
    )");
    0.56
    ]));
    0.56
     Trop
    0.53
    "));
    0.53
    Trop
    0.51
    ')],
    0.51
    conio
    0.51
    Activations Density 7.475%

    No Known Activations