© 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. 8907
    Prev
    Next
    INDEX
    Explanations

    phrases about planning and intentions

    oai_token-act-pair · 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
    principalTable
    -0.90
    NUMX
    -0.66
     africana
    -0.62
    ướng
    -0.59
    ubourg
    -0.58
    AllAfrica
    -0.57
    MessageOf
    -0.57
    stdbool
    -0.57
    \{\\
    -0.56
    jface
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.44
    Бахар
    0.44
    kháu
    0.43
     postIndex
    0.42
    ربای
    0.42
    PageIndex
    0.42
    HtmlAttribute
    0.41
    żesz
    0.41
    IntoConstraints
    0.40
     résulte
    0.39
    Activations Density 1.902%

    No Known Activations