© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11374
    Prev
    Next
    INDEX
    Explanations

    words in non-English languages or informal conversational language

    oai_token-act-pair · gemini-2.0-flash

    Sharing updates/information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     AspNetCore
    -0.61
    ্ষ
    -0.53
    cshtml
    -0.49
    MPN
    -0.47
    izophren
    -0.47
    ThemeOverlay
    -0.47
     ExecuteAsync
    -0.46
     gian
    -0.45
    saraba
    -0.45
    Huge
    -0.44
    POSITIVE LOGITS
     houſe
    0.77
     buurt
    0.71
     Houſe
    0.70
     féminine
    0.69
     Efq
    0.68
     voisins
    0.67
     supérieurs
    0.67
     HasFactory
    0.66
     فريبيس
    0.66
     quæ
    0.65
    Activations Density 1.379%

    No Known Activations