© 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. 1640
    Prev
    Next
    INDEX
    Explanations

    calls to action relating to websites or shops

    oai_token-act-pair · gemini-2.0-flash

    the word 'have' in various forms

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

    having, have

    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
     مشين
    -0.54
    insegna
    -0.50
     MonoBehaviour
    -0.50
    thouse
    -0.49
    blum
    -0.48
    PyExc
    -0.48
    adeira
    -0.47
    '));
    -0.47
    bibitem
    -0.47
    *********/
    -0.47
    POSITIVE LOGITS
    having
    0.77
    TestingModule
    0.72
    twimg
    0.71
     having
    0.68
     HAVING
    0.68
    have
    0.65
    Have
    0.62
    Having
    0.60
    HAVE
    0.59
     Having
    0.58
    Activations Density 1.423%

    No Known Activations