© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9140
    Prev
    Next
    INDEX
    Explanations

    relative comparisons using the word "more".

    oai_token-act-pair · gemini-2.0-flash

    the concept of 'more' and related comparative terms

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

    more

    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
    ValueStyle
    -0.47
     profonda
    -0.46
     ringan
    -0.45
     certes
    -0.42
     spē
    -0.39
    sság
    -0.38
     spesa
    -0.36
     rotina
    -0.35
    かなり
    -0.35
    mű
    -0.35
    POSITIVE LOGITS
    IntoConstraints
    0.90
     then
    0.83
     mergeFrom
    0.75
     THEN
    0.73
    then
    0.72
     civilised
    0.70
    Then
    0.68
     palatable
    0.67
     barbaric
    0.67
     Then
    0.66
    Activations Density 1.641%

    No Known Activations