© 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. 1826
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "less" or variations of it

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "less"

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

    less

    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
    CloseOperation
    -0.93
     ModelExpression
    -0.92
    LookAnd
    -0.83
    RenderAtEndOf
    -0.80
    Personensuche
    -0.80
    oredCriteria
    -0.77
    IndentedString
    -0.76
     '\\;'
    -0.75
     AssemblyCompany
    -0.75
    قایناق‌لار
    -0.75
    POSITIVE LOGITS
    합
    0.52
     volta
    0.47
    Responsive
    0.47
     iterable
    0.45
    iste
    0.44
    idere
    0.44
     responsive
    0.44
    forth
    0.42
    Sint
    0.42
     rit
    0.42
    Activations Density 3.499%

    No Known Activations