© 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. 11111
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Math

    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
     RSSSF
    -0.55
    reht
    -0.52
    ContentAsync
    -0.50
    Alc
    -0.48
     Tract
    -0.47
     Benth
    -0.46
    伯
    -0.45
     ledig
    -0.45
     Stä
    -0.44
    toISOString
    -0.44
    POSITIVE LOGITS
     Paglinawan
    0.79
    पया
    0.75
     referenties
    0.75
    Personensuche
    0.74
    \{\\
    0.74
     متعلقه
    0.71
    RUnlock
    0.69
    RenderAtEndOf
    0.69
     OFDb
    0.67
    ἶ
    0.66
    Activations Density 4.679%

    No Known Activations