© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2991
    Prev
    Next
    INDEX
    Explanations

    words suffixed with "al", words related to legal matters or words with numbers or quantities mixed in with the word.

    oai_token-act-pair · gemini-2.0-flash

    Generality or belonging

    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
    Negative Logits
     Efq
    -1.23
     Diſ
    -1.20
     ſche
    -1.20
     myſelf
    -1.19
     houſe
    -1.19
     ſta
    -1.17
     pleaſure
    -1.17
     purpoſe
    -1.16
     itſelf
    -1.16
    OGND
    -1.14
    POSITIVE LOGITS
    ly
    0.54
    a
    0.52
    <eos>
    0.49
     the
    0.48
    e
    0.45
    .*")]
    0.45
     سكانية
    0.43
     a
    0.41
     O
    0.40
     future
    0.39
    Activations Density 3.075%

    No Known Activations