© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11556
    Prev
    Next
    INDEX
    Explanations

    words and short phrases used in technical documents

    oai_token-act-pair · gemini-2.0-flash

    Something being stopped

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     trained
    -0.72
     developed
    -0.60
     inspired
    -0.58
     experienced
    -0.56
     Trained
    -0.55
    trained
    -0.53
     presented
    -0.52
    Trained
    -0.52
     motivated
    -0.52
     Developed
    -0.50
    POSITIVE LOGITS
     closed
    0.84
     Closed
    0.78
     cancelled
    0.76
    removed
    0.76
     blocked
    0.76
     removed
    0.76
    Closed
    0.76
     CLOSED
    0.75
     suppressed
    0.75
     separated
    0.75
    Activations Density 9.051%

    No Known Activations