© 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. 13961
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, references to studies, and enumeration such as i, ii, iii, or a, b, c.

    oai_token-act-pair · gemini-2.0-flash

    math notation and lists

    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
    abstractmethod
    -0.56
    amazonaws
    -0.52
    bibitem
    -0.50
     doInBackground
    -0.49
    OnAdd
    -0.48
    المشاركات
    -0.47
    ToBounds
    -0.47
     pylori
    -0.47
     and
    -0.47
    DataMember
    -0.46
    POSITIVE LOGITS
    gameserver
    0.58
     industriels
    0.58
     professionnels
    0.58
    >>;
    0.56
     collectivités
    0.55
     commerciaux
    0.55
    MigrationBuilder
    0.55
     militaires
    0.54
     rédaction
    0.54
     sportifs
    0.54
    Activations Density 0.956%

    No Known Activations