© 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. 15324
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially those related to file paths, compilation, and network communication, like in C, C++, or Javascript.

    oai_token-act-pair · gemini-2.0-flash

    sep

    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
    +#+
    -0.72
    ++
    -0.69
     Roskov
    -0.63
    mogat
    -0.61
    modelBuilder
    -0.60
    Hozzá
    -0.59
     Signalez
    -0.59
    eapples
    -0.58
    κτηρισ
    -0.58
    ]));
    -0.57
    POSITIVE LOGITS
    stateProvider
    0.52
    ByExample
    0.49
    DropTable
    0.46
    queryInterface
    0.44
    Configurer
    0.44
    乓
    0.44
     <<<<<<<<<<<<<<
    0.42
    auda
    0.42
    adpleegd
    0.41
    SafeMath
    0.41
    Activations Density 3.610%

    No Known Activations