© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5368
    Prev
    Next
    INDEX
    Explanations

    seemingly random characters, numbers, and punctuation, sometimes near a few words related to fiction.

    oai_token-act-pair · gemini-2.0-flash

    say "A"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     a
    -2.72
     an
    -1.72
    a
    -1.56
     sebuah
    -1.20
     eine
    -1.15
     seorang
    -1.08
     một
    -1.06
    an
    -1.05
     einen
    -1.04
    eine
    -1.04
    POSITIVE LOGITS
    enderror
    0.56
    findpost
    0.50
    ambilan
    0.50
    رشف
    0.50
    хьтан
    0.49
    nikami
    0.49
    errHandler
    0.48
    Diwedd
    0.47
    MessageTagHelper
    0.47
    devamını
    0.47
    Activations Density 7.416%

    No Known Activations