© 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. 7445
    Prev
    Next
    INDEX
    Explanations

    code snippets, logs or debugging information

    oai_token-act-pair · 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
    ,
    -0.68
     “
    -0.62
    ’
    -0.54
    -0.50
    ,”
    -0.49
    )
    -0.49
    -
    -0.48
    ).
    -0.48
    .
    -0.46
     
    -0.45
    POSITIVE LOGITS
     Monfieur
    1.45
     auroit
    1.44
     avoient
    1.44
     enfans
    1.43
     myſelf
    1.43
     purpoſe
    1.41
     ainfi
    1.38
     auffi
    1.38
     itſelf
    1.38
     quæ
    1.37
    Activations Density 28.759%
    No Known Activations