© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15083
    Prev
    Next
    INDEX
    Explanations

    words that indicate action, objectives, conflicts, and plots points

    oai_token-act-pair · gemini-2.0-flash

    save/saving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     save
    -1.34
     saved
    -1.23
     saving
    -1.20
    Save
    -1.17
     saves
    -1.16
     Save
    -1.16
    save
    -1.15
    Saving
    -1.04
     Saving
    -1.02
    saving
    -1.01
    POSITIVE LOGITS
     >=",
    0.78
     kaynağından
    0.70
    ynomial
    0.69
     typelib
    0.69
     betweenstory
    0.68
    __":
    0.66
     getItemCount
    0.66
     cérémonie
    0.65
     CommonModule
    0.65
    "]();
    0.65
    Activations Density 51.338%

    No Known Activations