© 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. 1842
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating a concept or procedure

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating states or attributes

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

    Scientific models and concepts

    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
     itſelf
    -0.75
    wiſe
    -0.70
    AntiForgeryToken
    -0.68
    ſelf
    -0.66
    eſt
    -0.66
    enumii
    -0.65
     themſelves
    -0.64
     ſtand
    -0.61
     Theſe
    -0.60
     ſeveral
    -0.60
    POSITIVE LOGITS
     is
    1.02
     has
    0.90
     isn
    0.77
     does
    0.74
     requires
    0.73
     doesn
    0.73
     was
    0.72
     allows
    0.71
     contains
    0.69
     gets
    0.68
    Activations Density 7.790%

    No Known Activations