© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4900
    Prev
    Next
    INDEX
    Explanations

    mentions of models and fashion designers, particularly in the context of financial or legal issues such as taxes and liens.

    oai_token-act-pair · gemini-2.0-flash

    Fashion and models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Autoritní
    -0.75
    thâu
    -0.68
    MemoryWarning
    -0.68
     gawas
    -0.65
    uxxxx
    -0.64
    XmlAccessType
    -0.63
    )++;
    -0.63
     مرئيه
    -0.61
    tagext
    -0.61
    WebMethod
    -0.60
    POSITIVE LOGITS
    nict
    0.48
     tibi
    0.41
     Safer
    0.40
    ત્ર
    0.39
     cré
    0.39
    JUN
    0.39
     junk
    0.39
    annotation
    0.37
     CreateTagHelper
    0.37
    cik
    0.36
    Activations Density 2.041%

    No Known Activations