© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5405
    Prev
    Next
    INDEX
    Explanations

    the word 'magic'

    oai_token-act-pair · gemini-2.0-flash

    magic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    InjectAttribute
    -0.73
    ########.
    -0.65
    AddTagHelper
    -0.62
    TargetException
    -0.62
     EconPapers
    -0.61
     jadx
    -0.61
    HtmlAttribute
    -0.59
    awtextra
    -0.56
     Normdatei
    -0.55
     ujednoznacz
    -0.54
    POSITIVE LOGITS
     собі
    0.57
     المعرف
    0.51
    ameran
    0.47
    ourke
    0.47
    gean
    0.47
    كويكب
    0.46
     censiti
    0.45
     tört
    0.44
     againſt
    0.43
    laise
    0.43
    Activations Density 4.037%

    No Known Activations