© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5276
    Prev
    Next
    INDEX
    Explanations

    the words 'the', commas, units of measure, and comparison phrases

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     alike
    -1.19
     onwards
    -0.94
     stessa
    -0.92
    respectively
    -0.89
     stesso
    -0.87
     respectively
    -0.86
     saja
    -0.85
     respectivamente
    -0.76
     whatsoever
    -0.76
     aforesaid
    -0.76
    POSITIVE LOGITS
    protoimpl
    0.79
    CloseOperation
    0.78
     виправивши
    0.75
     mxArray
    0.71
     Chwiliwch
    0.68
     CreateTagHelper
    0.64
    CodeAttribute
    0.63
    <bos>
    0.63
    EndGlobalSection
    0.63
    "),
    0.59
    Activations Density 2.044%

    No Known Activations