© 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. 1563
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and "this", and phrases of the form "have/has been a" and "been the subject"

    oai_token-act-pair · gemini-2.0-flash

    terms related to "subject" or "sub"

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

    Discussing a topic

    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
     ModelExpression
    -0.81
    exitRule
    -0.68
    Искәрмәләр
    -0.67
     mxArray
    -0.65
    Personendaten
    -0.61
     للمعارف
    -0.60
    Werde
    -0.60
    Jeografia
    -0.59
     发表于
    -0.59
    PerformLayout
    -0.59
    POSITIVE LOGITS
    sub
    0.84
     sub
    0.84
    Sub
    0.75
     Sub
    0.71
    object
    0.66
    サブ
    0.63
    SUB
    0.60
     object
    0.59
     SUB
    0.59
     sube
    0.58
    Activations Density 1.324%

    No Known Activations