© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11952
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "os" and the acronym "OSM" usually related to code or software

    oai_token-act-pair · gemini-2.0-flash

    os

    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
    writeField
    -0.81
    AndroidJUnit
    -0.72
    addContainerGap
    -0.71
     فريبيس
    -0.70
    scriptcase
    -0.69
     виправивши
    -0.69
    BeginInit
    -0.68
    CppMethod
    -0.66
    Hochspringen
    -0.66
    
    -0.65
    POSITIVE LOGITS
    });*/
    0.54
    })*/
    0.48
    )++;
    0.48
     Tempel
    0.47
    ็จ
    0.45
    lorette
    0.44
    usercontent
    0.44
     acred
    0.43
     Noël
    0.43
     }}"></
    0.42
    Activations Density 0.485%

    No Known Activations