© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5299
    Prev
    Next
    INDEX
    Explanations

    HTML, Javascript, PHP, and Portuguese language computer code and text

    oai_token-act-pair · gemini-2.0-flash

    Portuguese javascript 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    principalTable
    -0.79
     للمعارف
    -0.78
    Tikang
    -0.77
    findpost
    -0.73
    +:+
    -0.71
    rungsseite
    -0.71
    ValueStyle
    -0.71
    +#+#
    -0.71
    ---*/
    -0.70
     sociaux
    -0.68
    POSITIVE LOGITS
    COR
    0.47
     arro
    0.46
     Dreh
    0.46
    nEnter
    0.46
    oyle
    0.46
    zot
    0.45
     al
    0.45
    mands
    0.45
    alm
    0.44
    weet
    0.43
    Activations Density 0.207%

    No Known Activations