© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3297
    Prev
    Next
    INDEX
    Explanations

    clinical trial documents with sections labeled Program Name and Brief Description.

    oai_token-act-pair · gemini-2.0-flash

    extracting information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     fernández
    -0.53
     houſe
    -0.49
     oxidase
    -0.48
     plex
    -0.47
     uſed
    -0.46
     Juillet
    -0.45
    UnsafeEnabled
    -0.44
     ſte
    -0.44
     bibliographies
    -0.44
     sánchez
    -0.43
    POSITIVE LOGITS
     Site
    0.88
     Case
    0.87
     Name
    0.87
     Form
    0.87
     Line
    0.86
     Package
    0.86
     Group
    0.86
     Plan
    0.85
     Method
    0.84
     Option
    0.84
    Activations Density 7.104%

    No Known Activations