© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7886
    Prev
    Next
    INDEX
    Explanations

    JavaScript code blocks including common keywords

    oai_token-act-pair · gemini-2.0-flash

    function

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Roskov
    -0.77
     “.
    -0.64
    .”
    -0.64
    “.
    -0.63
    ”.
    -0.60
    RegressionTest
    -0.59
    mitives
    -0.57
     nahilalakip
    -0.56
    جمعیت
    -0.56
    fromnode
    -0.56
    POSITIVE LOGITS
     onClose
    0.56
     (
    0.54
     getCity
    0.54
     addItem
    0.54
     reloadData
    0.53
     getList
    0.53
     handleChange
    0.52
     getNum
    0.52
     getAddress
    0.52
     onSave
    0.52
    Activations Density 6.393%

    No Known Activations