© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9260
    Prev
    Next
    INDEX
    Explanations

    code related to vertices and object loading and UI elements, possibly in Objective-C.

    oai_token-act-pair · gemini-2.0-flash

    lists and arrays

    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
    Negative Logits
    AndEndTag
    -0.79
    windowFixed
    -0.72
     beginnetje
    -0.69
    ftagPool
    -0.69
    TintMode
    -0.63
    uaire
    -0.61
     AssemblyCulture
    -0.60
    Geplaatst
    -0.60
    InitVars
    -0.59
    ंदीखरीदारी
    -0.59
    POSITIVE LOGITS
     întâ
    0.51
     intéress
    0.49
    رشف
    0.48
     stampa
    0.46
     étranger
    0.45
     scuro
    0.44
    vosti
    0.43
     señora
    0.42
    occasione
    0.42
     pasos
    0.41
    Activations Density 6.536%

    No Known Activations