© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10459
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code in languages like Javascript or C

    oai_token-act-pair · gemini-2.0-flash

    code tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.91
     himſelf
    -0.82
     myſelf
    -0.79
     Мексичка
    -0.79
     Савезне
    -0.79
     themſelves
    -0.77
     Jefus
    -0.77
     becauſe
    -0.75
     whoſe
    -0.75
     Monfieur
    -0.74
    POSITIVE LOGITS
    int
    0.65
    ”
    0.54
    //
    0.54
     //
    0.54
    add
    0.52
    net
    0.51
    <eos>
    0.49
    less
    0.49
    emp
    0.49
    );
    0.48
    Activations Density 8.494%

    No Known Activations