© 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. 1903
    Prev
    Next
    INDEX
    Explanations

    words and phrases connecting causes to effects, often related to legal or systemic issues.

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating consequences or results

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

    Code and legal snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     found
    -0.64
     find
    -0.60
    पया
    -0.58
    find
    -0.53
    found
    -0.51
    QtGui
    -0.49
    Учитель
    -0.49
     Find
    -0.48
    Find
    -0.48
     finds
    -0.47
    POSITIVE LOGITS
    帖最后由
    0.77
     cometh
    0.60
     occurred
    0.56
     follows
    0.55
     occured
    0.54
    ExtendWith
    0.54
     ocur
    0.54
     entgegen
    0.53
     emerges
    0.53
    )"),
    0.53
    Activations Density 2.997%

    No Known Activations