© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15725
    Prev
    Next
    INDEX
    Explanations

    Indian names and words

    oai_token-act-pair · gemini-2.0-flash

    Indian contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     myſelf
    -0.80
    makeConstraints
    -0.79
    Tikang
    -0.78
    ViewFeatures
    -0.76
    parsedMessage
    -0.76
     Efq
    -0.74
    HtmlAttribute
    -0.74
    CloseOperation
    -0.73
     Nymp
    -0.73
     tranſ
    -0.72
    POSITIVE LOGITS
    kohl
    0.45
     Uhr
    0.42
    §
    0.41
     honour
    0.40
    icionar
    0.39
     recognise
    0.39
     Bhai
    0.39
    ได้
    0.39
     §
    0.38
    erst
    0.38
    Activations Density 2.129%

    No Known Activations