© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    words and short phrases that seem to be Indic in origin (likely Sanskrit or a related language)

    oai_token-act-pair · gemini-2.0-flash

    ya

    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
    ya
    -2.89
    YA
    -2.11
    Ya
    -1.51
    yaa
    -1.44
     ya
    -1.38
    yah
    -1.29
     Ya
    -1.25
    yas
    -1.12
    yā
    -1.00
     YA
    -0.93
    POSITIVE LOGITS
    -------
    0.64
    IntoConstraints
    0.63
     resourceCulture
    0.62
     AssemblyCulture
    0.62
     AssemblyTitle
    0.60
    verifyException
    0.60
    RTGC
    0.60
    存于互联网档案馆
    0.60
     transfieras
    0.59
    ########.
    0.57
    Activations Density 1.271%

    No Known Activations