© 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. 7076
    Prev
    Next
    INDEX
    Explanations

    HTML code, especially related to forms

    oai_token-act-pair · gemini-2.0-flash

    <

    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
     forms
    -1.09
     form
    -1.08
     Forms
    -1.02
     FORMS
    -0.95
     Form
    -0.95
    forms
    -0.92
    FORMS
    -0.85
     FORM
    -0.83
     форм
    -0.82
     Formen
    -0.81
    POSITIVE LOGITS
    input
    0.69
    पया
    0.51
    label
    0.49
    kegaard
    0.49
    Personendaten
    0.48
     Pilate
    0.45
    Input
    0.44
    oczes
    0.44
     Bourgoin
    0.44
    További
    0.44
    Activations Density 0.357%

    No Known Activations