© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    text that includes source code fragments or non-English sentences, specifically looking for code structures like null checks or elements of romance languages

    oai_token-act-pair · gemini-2.0-flash

    "of" in multiple languages

    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
     or
    -2.17
     или
    -1.25
    或
    -1.18
    或者
    -1.09
    หรือ
    -1.08
    或是
    -1.05
     或
    -1.00
    or
    -0.97
    或者是
    -0.96
    거나
    -0.94
    POSITIVE LOGITS
     of
    1.74
     của
    1.06
    of
    1.05
     Of
    1.03
    Of
    0.97
    ofthe
    0.88
    ของ
    0.87
     ofthe
    0.82
     OF
    0.79
    オブ
    0.77
    Activations Density 0.961%

    No Known Activations