© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    sections of code in php files

    oai_token-act-pair · gemini-2.0-flash

    php

    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
     import
    -1.20
     Import
    -1.08
     export
    -0.89
     importing
    -0.85
    Import
    -0.85
     imports
    -0.84
     Export
    -0.82
     Importing
    -0.81
    import
    -0.80
    Importing
    -0.79
    POSITIVE LOGITS
     purpoſe
    0.92
     Monfieur
    0.71
     excès
    0.71
     alluminio
    0.69
     démocr
    0.68
     malheure
    0.68
     ſtate
    0.68
     feroit
    0.68
     ſmall
    0.67
     pleaſure
    0.67
    Activations Density 0.674%

    No Known Activations