© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2513
    Prev
    Next
    INDEX
    Explanations

    Arabic names, especially those starting with "al", "ibn", "Nas", "Har", "Kir", and "Su" and/or ending in "yya"

    oai_token-act-pair · gemini-2.0-flash

    ith

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     your
    -0.47
    ecma
    -0.45
     res
    -0.44
    encodeWith
    -0.43
     effetto
    -0.42
     within
    -0.42
    logous
    -0.41
    omalainen
    -0.41
    tvar
    -0.41
    -
    -0.41
    POSITIVE LOGITS
     يتيمه
    1.35
    RegistryLite
    0.73
    المناصب
    0.69
     CreateTagHelper
    0.69
    WebElementEntity
    0.68
    enterOuterAlt
    0.67
     blessés
    0.66
    ''')
    0.66
    findpost
    0.64
     SEDS
    0.63
    Activations Density 0.427%

    No Known Activations