© 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. 12490
    Prev
    Next
    INDEX
    Explanations

    numbers or values

    oai_token-act-pair · gemini-2.0-flash

    numbers and measurements

    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
    ,
    -0.57
    <eos>
    -0.50
     Sche
    -0.49
     (
    -0.48
      
    -0.46
    ⓧ
    -0.46
     //
    -0.43
     le
    -0.43
     =
    -0.43
    ↵↵
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.97
    PerformLayout
    0.96
     تانيه
    0.93
    enterOuterAlt
    0.93
     AssemblyProduct
    0.93
    ValueStyle
    0.92
     يتيمه
    0.91
    RenderAtEndOf
    0.91
     Walkover
    0.91
     purpoſe
    0.89
    Activations Density 3.146%

    No Known Activations