© 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. 11392
    Prev
    Next
    INDEX
    Explanations

    personal opinions and anecdotes about the speaker's experiences

    oai_token-act-pair · gemini-2.0-flash

    personal stories

    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
    DeleteBehavior
    -0.71
    PerformLayout
    -0.66
     يتيمه
    -0.58
    richTextPanel
    -0.57
    Jeografia
    -0.54
    
    -0.54
     beginnetje
    -0.54
    IUrlHelper
    -0.53
    SerializedSize
    -0.52
    GEBURTS
    -0.52
    POSITIVE LOGITS
     propTypes
    0.57
    setViewName
    0.55
    ITTLE
    0.54
    OrderID
    0.53
    roduction
    0.53
    neming
    0.53
    DNEY
    0.52
     Doctrine
    0.52
     Kitt
    0.52
     Zwick
    0.51
    Activations Density 2.788%

    No Known Activations