© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8800
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with scientific procedures and measurements

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    inerja
    -0.58
    Str
    -0.45
     himself
    -0.44
    ίες
    -0.43
    endregion
    -0.43
    Gee
    -0.43
     folos
    -0.42
    Commercial
    -0.42
     Te
    -0.41
    Бра
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.74
    RectangleBorder
    0.71
    ")));
    0.69
    }));
    0.69
     Мексичка
    0.66
     unknownFields
    0.66
     оригіналу
    0.64
     AssemblyCompany
    0.63
    letoe
    0.62
     Theſe
    0.62
    Activations Density 0.673%

    No Known Activations