© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6599
    Prev
    Next
    INDEX
    Explanations

    capital letters, particularly when followed by other capitalized letters and/or certain Italian-related words

    oai_token-act-pair · gemini-2.0-flash

    Unconventional text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     e
    -0.76
    TagHelpers
    -0.48
     références
    -0.48
    "".
    -0.46
    눠
    -0.45
    рино
    -0.43
    ''.
    -0.42
    UIApplication
    -0.42
    addGap
    -0.42
    numerusform
    -0.42
    POSITIVE LOGITS
    IBOutlet
    0.64
     EventArgs
    0.60
     незавершена
    0.59
     ddelweddau
    0.57
     uintptr
    0.57
     HttpNotFound
    0.56
     autorytatywna
    0.56
     дописавши
    0.56
     AssemblyVersion
    0.55
    期刊论文
    0.54
    Activations Density 0.234%

    No Known Activations