© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15568
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gemini-2.0-flash

    Roman numerals

    np_token-act-pair-logits · gpt-4o-mini

    Roman numerals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -0.62
     myſelf
    -0.58
    modelBuilder
    -0.57
    ^(@)
    -0.56
     uſed
    -0.56
     Lard
    -0.55
     uſe
    -0.54
     Jefus
    -0.54
    RepeatedField
    -0.53
    ſelf
    -0.53
    POSITIVE LOGITS
     II
    2.11
     III
    2.02
    II
    1.91
    III
    1.87
     IV
    1.80
    IV
    1.59
     ii
    1.56
     VII
    1.48
     VI
    1.43
    Ⅱ
    1.43
    Activations Density 3.984%

    No Known Activations