© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1317
    Prev
    Next
    INDEX
    Explanations

    contexts including references to scientific publications, scientific data, or math formulas, especially when describing the measurement of some quantity.

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     мәкал
    -0.82
     '\\;'
    -0.80
    InjectAttribute
    -0.79
    يكب
    -0.76
    kháu
    -0.74
    цездатний
    -0.74
    AddTagHelper
    -0.73
    spesies
    -0.72
    astéro
    -0.72
     propOrder
    -0.72
    POSITIVE LOGITS
    1
    2.17
    2
    1.83
    3
    1.72
    4
    1.65
    6
    1.59
    9
    1.56
    5
    1.55
    7
    1.51
    8
    1.48
    0
    1.36
    Activations Density 27.247%

    No Known Activations