© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8331
    Prev
    Next
    INDEX
    Explanations

    Java code syntax

    oai_token-act-pair · gemini-2.0-flash

    unusual or obscure text patterns

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    .
    -0.75
    ,
    -0.63
     the
    -0.59
     en
    -0.56
     a
    -0.56
     il
    -0.54
     le
    -0.53
     in
    -0.52
     
    -0.51
     N
    -0.50
    POSITIVE LOGITS
     itſelf
    1.07
     pleaſure
    0.99
     Houſe
    0.98
     ―――――
    0.93
     myſelf
    0.91
     Monfieur
    0.89
     Theſe
    0.89
     ་་
    0.88
     AssemblyCompany
    0.87
     Diſ
    0.86
    Activations Density 0.945%

    No Known Activations