© 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. 12373
    Prev
    Next
    INDEX
    Explanations

    words describing the process of creating cards

    oai_token-act-pair · gemini-2.0-flash

    Crafting blog posts

    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
     kasarigan
    -0.55
    Super
    -0.53
    TR
    -0.52
    uminense
    -0.49
     Super
    -0.48
    ̀nh
    -0.48
    super
    -0.46
     gravitational
    -0.45
    inheritdoc
    -0.45
    screen
    -0.44
    POSITIVE LOGITS
    neſs
    0.81
    esterday
    0.73
    ^(@)
    0.70
     Anſ
    0.68
    Referències
    0.68
    ſelves
    0.67
     ExecuteAsync
    0.65
    ंदीखरीदारी
    0.64
     iſt
    0.63
     dieß
    0.63
    Activations Density 0.846%

    No Known Activations