© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10206
    Prev
    Next
    INDEX
    Explanations

    a mix of Kannada script and English text, possibly related to books or summaries

    oai_token-act-pair · gemini-2.0-flash

    ಭ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AddTagHelper
    -0.89
    \{\\
    -0.68
    RenderAtEndOf
    -0.68
     MediatR
    -0.66
    withstanding
    -0.66
    RetentionPolicy
    -0.65
     initComponents
    -0.64
     विश्वसनीयता
    -0.61
    tagHelperRunner
    -0.60
     ddelweddau
    -0.59
    POSITIVE LOGITS
    DropColumn
    0.68
     pincel
    0.52
    Bonus
    0.50
     peores
    0.48
     Вікіпе
    0.47
    Spoljašnje
    0.47
     mối
    0.47
    IVAS
    0.45
     Bonus
    0.45
    BONUS
    0.44
    Activations Density 7.661%

    No Known Activations